wayfinder
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external issue trackers and local project files (e.g.,
docs/agents/feature-list.md). This constitutes an attack surface where maliciously crafted issue descriptions or project documentation could influence the agent's planning logic or task breakdown. - Ingestion points: Reads issue tracker overviews and decision items; reads local product documents, specifications, and feature lists.
- Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the ingested issue data.
- Capability inventory: The skill can create, assign, and close issues in the tracker, as well as invoke other agent skills like
research,prototype, andwizard. - Sanitization: There are no explicit instructions for validating or sanitizing retrieved issue content before it is processed by the agent.
Audit Metadata