wayfinder
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from a repository's issue tracker, including ticket bodies and map descriptions. This creates an attack surface where malicious instructions embedded in tickets could influence the agent's behavior during research, prototyping, or discussion tasks.\n
- Ingestion points: Issue tracker tickets and the "map" issue body (SKILL.md) are retrieved by the agent at runtime.\n
- Boundary markers: The skill uses markdown headers for structure (e.g., ## Question) but does not include explicit instructions for the model to ignore embedded prompts or untrusted instructions within those sections.\n
- Capability inventory: The agent has capabilities to create and close issues, post comments, spawn research subagents, and generate prototype artifacts (SKILL.md).\n
- Sanitization: There is no evidence of sanitization, escaping, or validation of the content retrieved from the issue tracker before it is processed by the agent.\n\n- [DYNAMIC_EXECUTION]: The skill generates "prototype" artifacts which can include UI or logic code based on user discussions. It also spawns subagents to perform research tasks, representing a multi-step execution flow where generated code or external research findings may influence subsequent agent actions.
Audit Metadata