wayfinder
Pass
Audited by Gen Agent Trust Hub on Oct 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill reads and processes data from an external issue tracker, including issue bodies and comments, to manage project maps and tickets. This content serves as input for determining next steps, such as creating new tickets or spawning research subagents.
- Ingestion points: The agent reads the map issue body and child ticket bodies from the project's issue tracker.
- Boundary markers: No specific delimiters or instructions to ignore embedded commands within the ingested content are mentioned.
- Capability inventory: The skill can create, modify, and close issues, assign users, add labels, spin up subagents, and push findings to git branches.
- Sanitization: There is no evidence of content sanitization or filtering for retrieved tracker data before it is processed.
- [COMMAND_EXECUTION]: The skill performs automated operations on the project's repository and issue tracker as part of its planning workflow.
- Actions include creating tickets with specific labels, wiring dependency relationships between issues, and pushing research results to new remote git branches. These operations are consistent with the skill's primary function of charting and navigating a project map.
Audit Metadata