wayfinder
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and acts upon content from an external issue tracker, creating an attack surface for data-driven instructions.\n
- Ingestion points: The agent fetches the 'map' issue body and individual 'ticket' issue bodies (markdown content) from a repository tracker during execution.\n
- Boundary markers: The skill employs markdown headers for structure (e.g., '## Question') but lacks explicit system-level instructions to ignore or sanitize embedded prompts within those external texts.\n
- Capability inventory: The skill is authorized to create issues, wire dependencies, post resolution comments, and spawn sub-agents such as
/researchor/prototypebased on the content of the tickets it reads.\n - Sanitization: The instructions do not define any validation or filtering mechanisms for the content retrieved from the external tracker before it influences the agent's next steps.
Audit Metadata