accessibility-testing
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEMETADATA_POISONINGINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is composed entirely of instructional markdown and does not contain any executable code, scripts, or binary payloads. It provides clear guidance and examples for standard accessibility auditing tasks.- [METADATA_POISONING]: A discrepancy exists between the author provided in the analysis context (seb1n) and the author listed in the file metadata (AI Agent Skills Community). This appears to be a common attribution for community-driven content rather than a malicious deception.- [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves analyzing untrusted external content (HTML snippets and URLs), which is a standard surface for indirect prompt injection. However, the capabilities defined in the skill are restricted to reporting and code suggestions, posing no significant risk to the host environment.
- Ingestion points: External URLs and HTML blocks provided by the user as described in the Usage section of SKILL.md.
- Boundary markers: Absent; the skill does not define specific delimiters for untrusted content.
- Capability inventory: Textual audit report generation and remediation code snippets as outlined in SKILL.md.
- Sanitization: Absent; the skill does not specify methods for sanitizing or filtering external input.
Audit Metadata