aria-deprecated-role
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of markdown documentation providing educational guidance and review steps for accessibility audits. It does not perform any automated actions, file system modifications, or network requests.
- [NO_CODE]: No scripts (Python, JavaScript, Shell) or configuration files are present in the skill, eliminating the possibility of direct remote code execution or malicious command injection via the skill's own logic.
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and analyze external codebase data, which is an inherent attack surface for indirect prompt injection. However, since the skill provides no functional capabilities (like tool execution or network access), the risk is negligible.
- Ingestion points: SKILL.md (instructions to "Search the codebase" and "Review the rendered markup").
- Boundary markers: None provided within the instruction set.
- Capability inventory: None; the skill contains no executable scripts or tool-use definitions.
- Sanitization: None; the skill relies on the agent's internal safety filters for processing external content.
Audit Metadata