recoup-internal-dev-ship-issue
Pass
Audited by Gen Agent Trust Hub on Aug 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes content from external GitHub issues. Maliciously crafted issue descriptions could attempt to influence the agent's behavior during implementation or verification phases.
- Ingestion points: GitHub tracking issues (Goal, proposed contract, source references) processed in SKILL.md.
- Boundary markers: Absent. The skill does not define specific delimiters for untrusted issue content.
- Capability inventory: Shell command execution (gh, curl, pnpm, vercel) and file system modification (writing code and tests).
- Sanitization: Not explicitly described for issue content before processing.
- [COMMAND_EXECUTION]: The skill utilizes several CLI tools including
gh,curl,pnpm, andvercelto manage deployments, run tests, and perform network requests. These are used within a standard development context to interact with the vendor's environment. - [EXTERNAL_DOWNLOADS]: The skill interacts with the
recoupableorganization's GitHub repositories to fetch code, documentation, and deployment statuses. These represent vendor-owned resources used for staff tooling.
Audit Metadata