web-quality-audit
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided code and project files for auditing purposes, which constitutes an ingestion point for untrusted data.
- Ingestion points: The skill analyzes user-provided HTML files and project structures via the
scripts/analyze.shscript. - Boundary markers: No specific delimiters or instructions to ignore embedded instructions within the audited files are provided in the prompt instructions.
- Capability inventory: The skill executes local shell commands through a script to perform static file analysis using
findandgrep. - Sanitization: The script uses read-only pattern matching to identify issues; no specific sanitization or escaping of the ingested file content is performed before presentation to the agent.
- [COMMAND_EXECUTION]: The skill includes a local bash script (
scripts/analyze.sh) that is executed to analyze project files. The script uses standard Unix utilities such asfind,grep, andechoto verify HTML structure and metadata. The operations are local, restricted to file reading, and do not involve network access or execution of remote code.
Audit Metadata