wayfinder
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the repository, including project maps, ticket files, and configuration files (AGENTS.md, CLAUDE.md). This creates a surface where malicious instructions embedded in these files could influence the agent's planning or execution of sub-tasks.
- Ingestion points: Reads content from
{agentRoot}/wayfinding/<effort>/map.md, individual ticket files in{agentRoot}/wayfinding/<effort>/tickets/, and configuration blocks inAGENTS.mdorCLAUDE.md. - Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded prompts within the markdown content of the tickets.
- Capability inventory: The agent has the capability to read/write filesystem files, spawn
/researchsubagents, and invoke external tools or skills such as/prototypeor/grilling. - Sanitization: There is no evidence of sanitization or validation performed on the markdown content before it is incorporated into the agent's context or used to drive logic.
Audit Metadata