wayfinder
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and act upon data from external sources that could contain malicious instructions.\n
- Ingestion points: The agent reads the 'map' issue body, individual ticket descriptions, resolution comments, and information from third-party APIs or documentation retrieved during 'research' tasks.\n
- Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions for the data ingested from the issue tracker or external resources.\n
- Capability inventory: The skill can create and modify issues on a tracker, push new Git branches (e.g., 'research/'), and dynamically invoke other platform tools based on instructions found in the 'Notes' section of the map.\n
- Sanitization: There are no explicit instructions for the agent to sanitize or validate the content of tickets or external resources before acting upon them.
Audit Metadata