audit-accessibility

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [NO_CODE]: The skill consists entirely of markdown-based instructions for accessibility auditing. It does not include any executable scripts, automated commands, or dependency configurations.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a process for reading external data from the docs/knowledge-base/ directory.
  • Ingestion points: Reads local documentation files to identify project invariants.
  • Boundary markers: None specified.
  • Capability inventory: The skill has no execution capabilities (network access, shell commands, or file system writes).
  • Sanitization: None specified. While this represents an attack surface for indirect prompt injection, the lack of tool-calling or script execution capabilities prevents any malicious exploitation within the scope of this skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 02:33 AM