Vulnerability-Lookup

GHSA-JV2H-4P9V-WF5W

Vulnerability from github – Published: 2026-06-19 15:12 – Updated: 2026-06-19 15:12

Summary

ouroboros-ai: Incomplete fix of CVE-2026-47211: untrusted project .env can still reach RCE via omitted execution-routing keys

Details

Impact

The CVE-2026-47211 fix (0.39.0) added _UNTRUSTED_ENV_DENYLIST to stop an untrusted project-directory .env from redirecting execution. The denylist was incomplete — several execution-routing keys of the same RCE class were omitted, so a malicious cloned repo can still reach arbitrary command execution by shipping a .env (auto-loaded at import, no review step):

Backend config-home roots CODEX_HOME, OPENCODE_CONFIG, OPENCODE_CONFIG_DIR, XDG_CONFIG_HOME: a spawned vendor CLI resolves its config from these. CODEX_HOME=./.evil + committed ./.evil/config.toml redirects the nested Codex agent to attacker config — mcp_servers.<name>.command/args (RCE) and approval_policy="never" / sandbox_mode="danger-full-access" (silent removal of the human approval gate). (reported by matte1782)
MCP bridge / plugin execution roster OUROBOROS_MCP_CONFIG (the YAML's server command/args are spawned via stdio_client — RCE), OUROBOROS_PLUGIN_LOCKFILE, OUROBOROS_PLUGIN_TRUST_ROOT (redirect the installed-plugin roster / trust root so ooo <name> dispatches into attacker code). (reported by hackkim)
SSRF guard toggle OUROBOROS_ALLOW_LOCAL_TRANSPORT (re-enables loopback/private MCP transport targets).
Instruction / capability roots OUROBOROS_AGENTS_DIR, COPILOT_CUSTOM_INSTRUCTIONS_DIRS (replace spawned sub-agent role prompts), OUROBOROS_RUNTIME_PROFILE (backend selector), OUROBOROS_TOOL_CAPABILITIES (override YAML can lower a tool's approval_class, weakening the approval gate).

Additionally, the MCP bridge auto-loaded ./.ouroboros/mcp_servers.yaml from the working directory (create_bridge_from_env(cwd=Path.cwd())), so running ooo inside a malicious repo spawned the committed roster's command — RCE with no .env at all. (cwd-branch noted by hackkim)

Patches

Fixed in 0.42.1. All listed keys were added to _UNTRUSTED_ENV_DENYLIST; the cwd auto-discovery branch was removed (only the explicit OUROBOROS_MCP_CONFIG env var and ~/.ouroboros/mcp_servers.yaml remain, both trusted). The regression suite now derives from the source denylist to prevent future drift.

Workarounds

Do not run Ouroboros from an untrusted/cloned repository directory; remove any project-directory .env and ./.ouroboros/mcp_servers.yaml before running.

Credit

Reported privately via coordinated disclosure by matte1782 and hackkim (https://github.com/hackkim).

Severity

8.6 (High)


                  
                    CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:A/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N

Show details on source website

JSON

To clipboard

{
  "affected": [
    {
      "database_specific": {
        "last_known_affected_version_range": "\u003c= 0.42.0"
      },
      "package": {
        "ecosystem": "PyPI",
        "name": "ouroboros-ai"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "0.42.1"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [],
  "database_specific": {
    "cwe_ids": [
      "CWE-15",
      "CWE-94"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2026-06-19T15:12:25Z",
    "nvd_published_at": null,
    "severity": "HIGH"
  },
  "details": "### Impact\nThe CVE-2026-47211 fix (0.39.0) added `_UNTRUSTED_ENV_DENYLIST` to stop an untrusted project-directory `.env` from redirecting execution. The denylist was incomplete \u2014 several execution-routing keys of the same RCE class were omitted, so a malicious cloned repo can still reach arbitrary command execution by shipping a `.env` (auto-loaded at import, no review step):\n\n- **Backend config-home roots** `CODEX_HOME`, `OPENCODE_CONFIG`, `OPENCODE_CONFIG_DIR`, `XDG_CONFIG_HOME`: a spawned vendor CLI resolves its config from these. `CODEX_HOME=./.evil` + committed `./.evil/config.toml` redirects the nested Codex agent to attacker config \u2014 `mcp_servers.\u003cname\u003e.command/args` (RCE) and `approval_policy=\"never\"` / `sandbox_mode=\"danger-full-access\"` (silent removal of the human approval gate). (reported by matte1782)\n- **MCP bridge / plugin execution roster** `OUROBOROS_MCP_CONFIG` (the YAML\u0027s server `command`/`args` are spawned via stdio_client \u2014 RCE), `OUROBOROS_PLUGIN_LOCKFILE`, `OUROBOROS_PLUGIN_TRUST_ROOT` (redirect the installed-plugin roster / trust root so `ooo \u003cname\u003e` dispatches into attacker code). (reported by hackkim)\n- **SSRF guard toggle** `OUROBOROS_ALLOW_LOCAL_TRANSPORT` (re-enables loopback/private MCP transport targets).\n- **Instruction / capability roots** `OUROBOROS_AGENTS_DIR`, `COPILOT_CUSTOM_INSTRUCTIONS_DIRS` (replace spawned sub-agent role prompts), `OUROBOROS_RUNTIME_PROFILE` (backend selector), `OUROBOROS_TOOL_CAPABILITIES` (override YAML can lower a tool\u0027s `approval_class`, weakening the approval gate).\n\nAdditionally, the MCP bridge auto-loaded `./.ouroboros/mcp_servers.yaml` from the working directory (`create_bridge_from_env(cwd=Path.cwd())`), so running `ooo` inside a malicious repo spawned the committed roster\u0027s `command` \u2014 RCE with no `.env` at all. (cwd-branch noted by hackkim)\n\n### Patches\nFixed in 0.42.1. All listed keys were added to `_UNTRUSTED_ENV_DENYLIST`; the cwd auto-discovery branch was removed (only the explicit `OUROBOROS_MCP_CONFIG` env var and `~/.ouroboros/mcp_servers.yaml` remain, both trusted). The regression suite now derives from the source denylist to prevent future drift.\n\n### Workarounds\nDo not run Ouroboros from an untrusted/cloned repository directory; remove any project-directory `.env` and `./.ouroboros/mcp_servers.yaml` before running.\n\n### Credit\nReported privately via coordinated disclosure by matte1782 and hackkim (https://github.com/hackkim).",
  "id": "GHSA-jv2h-4p9v-wf5w",
  "modified": "2026-06-19T15:12:25Z",
  "published": "2026-06-19T15:12:25Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/Q00/ouroboros/security/advisories/GHSA-jv2h-4p9v-wf5w"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/Q00/ouroboros"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:A/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N",
      "type": "CVSS_V4"
    }
  ],
  "summary": "ouroboros-ai: Incomplete fix of CVE-2026-47211: untrusted project .env can still reach RCE via omitted execution-routing keys"
}

CVE-2026-66065 (GCVE-0-2026-66065)

Vulnerability from cvelistv5 – Published: 2026-08-03 20:20 – Updated: 2026-08-05 14:20

Title

Ouroboros: Untrusted project .env can still reach RCE via omitted execution-routing keys (Incomplete fix of CVE-2026-47211)

Summary

Ouroboros is a local-first runtime for AI coding agents that records their actions and applies user-defined policies to constrain behavior. Versions prior to 0.42.1 have an incomplete denylist. Several execution-routing keys of the same RCE class were omitted, so a malicious cloned repo can still reach arbitrary command execution by shipping a .env (auto-loaded at import, with no review step). The CVE-2026-47211 fix added _UNTRUSTED_ENV_DENYLIST to stop an untrusted project-directory .env from redirecting execution, but it did not account for all keys. The backend config-home and MCP/plugin roots bypass the approval gate by pointing the nested agent, MCP servers, and plugin roster at attacker config. Other variables re-enable blocked local transports, replace sub-agent prompts, switch backends, and lower tool approval classes, further weakening the approval gate. This issue has been fixed in version 0.42.1.

Severity

8.4 (High)


                        
                          CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:A/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N

SSVC

Exploitation: none Automatable: no Technical Impact: total

CISA Coordinator · CISA-ADP (v2.0.3)

Decision recorded 2026-08-05 14:20 UTC

CWE

CWE-15 - External Control of System or Configuration Setting
CWE-94 - Improper Control of Generation of Code ('Code Injection')

Assigner

GitHub_M mitre root Scorecard

References

2 references

URL	Tags
https://github.com/Q00/ouroboros/security/advisor…	x_refsource_CONFIRM
https://github.com/Q00/ouroboros/releases/tag/v0.42.1	x_refsource_MISC

Impacted products

1 product

Vendor	Product	Version
Q00	ouroboros	Affected: < 0.42.1

Show details on NVD website

JSON

To clipboard

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2026-66065",
                "options": [
                  {
                    "Exploitation": "none"
                  },
                  {
                    "Automatable": "no"
                  },
                  {
                    "Technical Impact": "total"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-08-05T14:20:43.116568Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-08-05T14:20:51.942Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "product": "ouroboros",
          "vendor": "Q00",
          "versions": [
            {
              "status": "affected",
              "version": "\u003c 0.42.1"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "Ouroboros is a local-first runtime for AI coding agents that records their actions and applies user-defined policies to constrain behavior. Versions prior to 0.42.1 have an incomplete denylist. Several execution-routing keys of the same RCE class were omitted, so a malicious cloned repo can still reach arbitrary command execution by shipping a .env (auto-loaded at import, with no review step). The CVE-2026-47211 fix added _UNTRUSTED_ENV_DENYLIST to stop an untrusted project-directory .env from redirecting execution, but it did not account for all keys. The backend config-home and MCP/plugin roots bypass the approval gate by pointing the nested agent, MCP servers, and plugin roster at attacker config. Other variables re-enable blocked local transports, replace sub-agent prompts, switch backends, and lower tool approval classes, further weakening the approval gate. This issue has been fixed in version 0.42.1."
        }
      ],
      "metrics": [
        {
          "cvssV4_0": {
            "attackComplexity": "LOW",
            "attackRequirements": "NONE",
            "attackVector": "LOCAL",
            "baseScore": 8.4,
            "baseSeverity": "HIGH",
            "privilegesRequired": "NONE",
            "subAvailabilityImpact": "NONE",
            "subConfidentialityImpact": "NONE",
            "subIntegrityImpact": "NONE",
            "userInteraction": "ACTIVE",
            "vectorString": "CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:A/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N",
            "version": "4.0",
            "vulnAvailabilityImpact": "HIGH",
            "vulnConfidentialityImpact": "HIGH",
            "vulnIntegrityImpact": "HIGH"
          }
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-15",
              "description": "CWE-15: External Control of System or Configuration Setting",
              "lang": "en",
              "type": "CWE"
            }
          ]
        },
        {
          "descriptions": [
            {
              "cweId": "CWE-94",
              "description": "CWE-94: Improper Control of Generation of Code (\u0027Code Injection\u0027)",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-08-03T20:20:27.599Z",
        "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "shortName": "GitHub_M"
      },
      "references": [
        {
          "name": "https://github.com/Q00/ouroboros/security/advisories/GHSA-jv2h-4p9v-wf5w",
          "tags": [
            "x_refsource_CONFIRM"
          ],
          "url": "https://github.com/Q00/ouroboros/security/advisories/GHSA-jv2h-4p9v-wf5w"
        },
        {
          "name": "https://github.com/Q00/ouroboros/releases/tag/v0.42.1",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/Q00/ouroboros/releases/tag/v0.42.1"
        }
      ],
      "source": {
        "advisory": "GHSA-jv2h-4p9v-wf5w",
        "discovery": "UNKNOWN"
      },
      "title": "Ouroboros: Untrusted project .env can still reach RCE via omitted execution-routing keys (Incomplete fix of CVE-2026-47211)"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
    "assignerShortName": "GitHub_M",
    "cveId": "CVE-2026-66065",
    "datePublished": "2026-08-03T20:20:27.599Z",
    "dateReserved": "2026-07-23T23:25:28.897Z",
    "dateUpdated": "2026-08-05T14:20:51.942Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2"
}

Sightings

Author	Source	Type	Date	Other

Nomenclature

Seen: The vulnerability was mentioned, discussed, or observed by the user.
Confirmed: The vulnerability has been validated from an analyst's perspective.
Published Proof of Concept: A public proof of concept is available for this vulnerability.
Exploited: The vulnerability was observed as exploited by the user who reported the sighting.
Patched: The vulnerability was observed as successfully patched by the user who reported the sighting.
Not exploited: The vulnerability was not observed as exploited by the user who reported the sighting.
Not confirmed: The user expressed doubt about the validity of the vulnerability.
Not patched: The vulnerability was not observed as successfully patched by the user who reported the sighting.

The MITRE ATT&CK techniques below are AI-generated suggestions, inferred from the description of the vulnerability by the CIRCL/vulnerability-attack-technique-classification-roberta-base model, served locally by ML-Gateway. They have not been verified by an analyst and are provided for guidance only.
The approach is described in our paper Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion.
Browse all ATT&CK techniques and the vulnerabilities related to each.

Related by attack behaviour

Vulnerabilities whose description is nearest to this one in the vector space of the CIRCL/vulnerability-attack-technique-biencoder model. This is a similarity search over the bi-encoder space (plain cosine), not a classification, and it has no measured accuracy.

Action not permitted