elite-audit
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill recommends the use of well-known development tools via npx, including Lighthouse, Unlighthouse, Vite Bundle Visualizer, and Source Map Explorer, to gather audit metrics from the project environment.
- [INDIRECT_PROMPT_INJECTION]: The skill audits untrusted project source code (HTML, CSS, JS) and metadata, creating a surface where malicious instructions embedded in the project could influence the agent's behavior.
- Ingestion points: Project source files (HTML, CSS, JS), build artifacts, and web content analyzed during the audit process (e.g., SKILL.md and references/critical-rules.md).
- Boundary markers: The instructions do not define specific delimiters or instructions to ignore potential commands embedded within the code being analyzed.
- Capability inventory: The skill recommends running command-line testing tools and invoking other specialized remediation skills (SKILL.md).
- Sanitization: No explicit sanitization or filtering logic is described for the content read from audited files.
Audit Metadata