web-quality-audit
Pass
Audited by Gen Agent Trust Hub on Aug 23, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill uses a bash script (scripts/analyze.sh) to perform static analysis of project files. The script is securely implemented, using proper variable quoting and restricting its operations to local file reading and pattern matching.
- [INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it processes untrusted HTML and project files. However, the risk is minimal as the automated analysis is limited to static pattern matching and the skill lacks network or write capabilities.
- Ingestion points: Project files analyzed by the agent and the included shell script.
- Boundary markers: Absent. The instructions do not specify delimiters or warnings for the agent to ignore instructions embedded within the code being audited.
- Capability inventory: The skill is restricted to static analysis (grep) and code review; it does not have network access or write permissions in its current scripts.
- Sanitization: None. HTML content is processed directly for pattern matching.
Audit Metadata