critique
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes HTML artifacts provided by the user or located within the project workspace. This functionality introduces an attack surface where malicious instructions could be embedded within the processed data to influence the agent's behavior.
- Ingestion points: The skill reads project files, pasted HTML code, or recently generated artifacts for scoring as described in the Workflow section of
SKILL.md. - Boundary markers: The instructions do not establish explicit boundary markers or warnings to separate user-provided data from agent instructions.
- Capability inventory: The skill possesses the capability to generate and emit HTML artifacts containing the analysis results.
- Sanitization: No sanitization or escaping protocols are specified for the content ingested during the review process.
- [EXTERNAL_DOWNLOADS]: The
example.htmlfile references external font assets from Google Fonts (fonts.googleapis.comandfonts.gstatic.com) to provide typography for the generated reports.
Audit Metadata