wayfinder
Pass
Audited by Gen Agent Trust Hub on Aug 10, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted data from an external issue tracker, creating a surface for indirect prompt injection attacks where malicious instructions in issue bodies could influence agent behavior.
- Ingestion points: Issue titles, bodies, and comments retrieved from a repository issue tracker as described in SKILL.md.
- Boundary markers: Absent; there are no instructions to use delimiters or ignore embedded commands when processing ticket content.
- Capability inventory: The skill can invoke sub-agents (/research, /prototype) and perform write operations (create/edit/close issues) on the tracker.
- Sanitization: No sanitization or validation of the retrieved issue data is specified before the agent processes it.
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent or user to execute a setup command from an external source not managed by the skill author.
- Evidence: Instruction to 'run /setup-matt-pocock-skills' found in the 'The Map' section of SKILL.md.
Audit Metadata