wayfinder
Pass
Audited by Gen Agent Trust Hub on Jul 27, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its reliance on external data from an issue tracker to guide agent behavior.
- Ingestion points: The agent reads and processes the 'map' issue and individual 'ticket' issues (titles, bodies, and comments) from the repository's issue tracker as described in SKILL.md.
- Boundary markers: There are no defined delimiters or instructions provided to the agent to distinguish between its own system instructions and potentially malicious instructions embedded within the ticket data.
- Capability inventory: The skill allows the agent to perform autonomous tasks ('AFK' mode), create git branches, and invoke powerful sub-skills like /research and /prototype based on the content of these tickets.
- Sanitization: The instructions do not specify any validation, filtering, or escaping of the content retrieved from the external tracker before it is interpolated into the agent's context.
Audit Metadata