wayfinder

Pass

Audited by Gen Agent Trust Hub on Jul 11, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect Prompt Injection Surface. The skill reads and processes ticket content (titles, questions, and descriptions) from a repository's issue tracker. Since these fields can be modified by any user with repository access, an attacker could potentially embed instructions aimed at manipulating the agent's behavior.
  • Ingestion points: The skill fetches ticket data and 'Decisions so far' from the repository's issue tracker (SKILL.md).
  • Boundary markers: The instructions do not provide specific delimiters or ignore-instructions to separate the retrieved data from the agent's core logic.
  • Capability inventory: The skill can invoke other agent capabilities like /grilling, /domain-modeling, and /prototype, and it can perform actions on the issue tracker such as posting resolution comments and closing tickets.
  • Sanitization: The skill does not include any explicit validation or sanitization mechanisms for the data retrieved from the issue tracker.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 11, 2026, 10:35 AM
Security Audit — agent-trust-hub — wayfinder