wayfinder
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external issue trackers which could contain instructions intended to influence agent behavior.
- Ingestion points: The agent reads issue titles, bodies, and comments from the repository's issue tracker (SKILL.md, lines 35, 96, 126).
- Boundary markers: No specific markers or delimiters are used to isolate untrusted content from child issues or comments.
- Capability inventory: The skill can create, edit, close, and assign issues, and trigger subagents for research and prototyping.
- Sanitization: No validation or sanitization of issue content is performed before the agent processes it.
- [COMMAND_EXECUTION]: The skill directs the user to run external setup commands.
- Evidence: The skill documentation (SKILL.md, line 37) instructs the agent to tell the user to run
/setup-matt-pocock-skillsif a tracker has not been provided.
Audit Metadata