github-commit-recovery
Pass
Audited by Gen Agent Trust Hub on Jun 7, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [UNVERIFIABLE_DEPENDENCIES_AND_REMOTE_CODE_EXECUTION]: The skill utilizes
curl,git fetch, and a Python script with therequestslibrary to download remote content from GitHub. These operations target a well-known service (GitHub) and are consistent with the forensic intent of the skill. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted commit data from external repositories, creating an attack surface for indirect prompt injection where malicious instructions could be embedded in commit diffs or metadata.
- Ingestion points: Commit data and patches fetched from
api.github.comandgithub.com(SKILL.md). - Boundary markers: Absent; there are no instructions for the agent to treat retrieved commit content as untrusted data or to ignore embedded instructions.
- Capability inventory: Includes network operations (
curl,requests) and local file system writes (Python snippet in SKILL.md). - Sanitization: Absent; retrieved content is processed or stored without validation or escaping.
Audit Metadata