debug-helper
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of markdown documentation, instructional guidelines, and usage examples. No executable scripts, binaries, or automated tool configurations are present.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and interpret external data sources, specifically error logs and stack traces, which could contain malicious instructions. 1. Ingestion points: User-supplied error descriptions and stack traces processed via the instructions in SKILL.md. 2. Boundary markers: None defined; instructions do not include specific delimiters or 'ignore' directives for processed content. 3. Capability inventory: The skill does not request or list any tools for command execution, network requests, or file system modifications. 4. Sanitization: The skill contains no logic for input validation, sanitization, or safety filtering of the ingested data.
Audit Metadata