wayfinder
Pass
Audited by Gen Agent Trust Hub on Aug 10, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes content from an external issue tracker (titles and bodies of issues/tickets) to guide its decision-making and planning process, creating a surface for indirect prompt injection.
- Ingestion points: Reading issue titles, bodies, and comments from the repository issue tracker (SKILL.md).
- Boundary markers: The instructions do not specify any delimiters or warnings to treat ticket content as untrusted data or to ignore embedded instructions.
- Capability inventory: The skill can invoke subagents (e.g., /research, /prototype), create/modify issues, and perform shell-based research tasks as described in the invocation logic (SKILL.md).
- Sanitization: There is no mention of explicit sanitization, validation, or escaping of the content retrieved from the issue tracker before it is used to drive agent actions.
Audit Metadata