web-quality-audit

Pass

Audited by Gen Agent Trust Hub on Mar 22, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted HTML content.
  • Ingestion points: HTML files and directories provided by the user for analysis in SKILL.md and through the scripts/analyze.sh script.
  • Boundary markers: Absent; there are no specific delimiters or instructions to ignore potential commands embedded within the HTML source code.
  • Capability inventory: The skill utilizes a bash script (using find and grep) to perform checks and instructs the agent to generate actionable code recommendations and fixes.
  • Sanitization: No content filtering, escaping, or validation of the analyzed HTML files is implemented before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 22, 2026, 11:49 AM