quality-expert
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill does not contain any malicious patterns, prompt injections, or unauthorized data access attempts. The instructions focus entirely on quality engineering philosophy and strategy.
- [NO_CODE]: The skill consists of Markdown instructions and metadata without any accompanying scripts, executables, or code files.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze external project files and web content, which presents a surface for indirect prompt injection. Ingestion points: Files accessed via Read, Glob, and Grep tools, and web content from WebFetch. Boundary markers: No specific delimiters are defined in the instructions for data interpolation. Capability inventory: The skill has read-only filesystem and network access via platform tools but no write or execution capabilities. Sanitization: No input validation or filtering logic is specified. The risk is assessed as safe because the behavior is integral to the skill's primary function and lacks high-impact capabilities.
Audit Metadata