troubleshoot
Pass
Audited by Gen Agent Trust Hub on Apr 2, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a structured diagnostic methodology, including established frameworks like OODA, 5 Whys, and binary search (Wolf Fence). Its operations are restricted to searching, reading local project files, and maintaining a local learning database.
- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it retrieves and processes content from external websites (via WebFetch) and handles user-provided error logs.
- Ingestion points: External website content retrieved through WebFetch (e.g., from Stack Overflow, GitHub) and user-supplied error descriptions in SKILL.md.
- Boundary markers: No specific delimiters or safety instructions are defined to separate untrusted external content from system instructions in protocols/search-multi-source.md.
- Capability inventory: Tools for WebSearch, WebFetch, Read, Glob, Grep, and AskUserQuestion. The skill also attempts to persist diagnostic data to the filesystem as noted in SKILL.md.
- Sanitization: There are no explicit instructions to sanitize or validate external content before it is processed by the agent.
Audit Metadata