wayfinder
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process information from an issue tracker, documentation, and APIs to resolve 'decision tickets'. This data directly influences the agent's logic and subsequent map updates.
- Ingestion points: Issue tracker titles, bodies, and comments, as well as third-party APIs and local knowledge bases (SKILL.md).
- Boundary markers: There are no instructions to the agent to use delimiters or ignore potentially malicious instructions embedded in the ingested data.
- Capability inventory: The skill can modify the issue tracker (create, close, and assign tickets), perform git operations (branch creation and pushing), and spawn subagents (SKILL.md).
- Sanitization: The instructions do not define any validation or sanitization logic for data retrieved from external sources.
- [COMMAND_EXECUTION]: The skill performs automated git operations and manages subagent execution as part of its core workflow.
- Evidence: Instructions include 'spin up a subagent that calls the Skill tool' and 'Push the branch but open no PR' (SKILL.md).
Audit Metadata