pick-an-issue
Pass
Audited by Gen Agent Trust Hub on Jul 29, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted external data which could contain malicious instructions designed to influence the agent.
- Ingestion points: The skill reads issue titles, bodies, and comments from external repositories in SKILL.md (Steps 2 and 3).
- Boundary markers: Absent. The instructions do not specify the use of delimiters or instructions to ignore embedded commands when processing backlog content.
- Capability inventory: The skill has the capability to write local files (foundry/missions//N.md) and execute a path resolution script as defined in SKILL.md.
- Sanitization: Absent. There is no requirement for the agent to sanitize or escape the content gathered from the external backlog before including it in the mission contract or presenting it to the user.
- [COMMAND_EXECUTION]: The skill instructs the agent to use a specific script to resolve the local source repository path.
- Evidence: SKILL.md references scripts/resolve-source-root.mjs as the canonical resolver for identifying the output directory. This script is a component of the skill's own repository infrastructure provided by the author.
Audit Metadata