wayfinder
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill reads and processes content from an external issue tracker, which serves as an untrusted ingestion surface for potential instructions.\n
- Ingestion points: The agent is instructed to load 'map body' content, 'child issues' (tickets), and 'tracker-specific documentation' as described in SKILL.md. The 'Notes' section in the map issue is specifically designed to override the skill's default behavior.\n
- Boundary markers: The skill does not provide instructions to use delimiters or to ignore commands that might be embedded in the issue tracker data.\n
- Capability inventory: The agent has the capability to create, close, and comment on issues, wire dependencies, and invoke other skills such as /research and /prototype.\n
- Sanitization: There is no mention of input validation or content sanitization for the data retrieved from the issue tracker.
Audit Metadata