alt-text
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill describes a code auditing workflow that ingests untrusted data from a codebase's HTML elements.
- Ingestion points: The agent is instructed to scan all elements in the source code as defined in SKILL.md.
- Boundary markers: The instructions do not define specific delimiters or security boundaries for the ingested content.
- Capability inventory: The skill is restricted to analysis and reporting; it does not utilize sensitive capabilities such as network access, system command execution, or file writing.
- Sanitization: No explicit sanitization is performed on the attribute values read from the code.
- [SAFE]: All external references in the skill, including links to W3C and the Frontend Checklist, point to well-known and reputable industry standards organizations.
Audit Metadata