accessibility-compliance-accessibility-audit-v2

Pass

Audited by Gen Agent Trust Hub on Aug 7, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill defines a potential attack surface for indirect prompt injection through the use of unvalidated user input.
  • Ingestion points: The SKILL.md file includes a $ARGUMENTS placeholder within the "Imported: Requirements" section to capture user-provided requirements.
  • Boundary markers: The skill lacks explicit delimiters or instructions directing the agent to ignore or isolate instructions that may be embedded within the provided arguments.
  • Capability inventory: The skill provides implementation templates in resources/implementation-playbook.md for browser automation (Puppeteer) and automated scanning (axe-core). If the agent's behavior is influenced by malicious input through $ARGUMENTS, these capabilities could be directed toward unintended targets.
  • Sanitization: No evidence of input sanitization, schema validation, or escaping was found for the data interpolated via $ARGUMENTS.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 7, 2026, 09:22 PM
Security Audit — agent-trust-hub — accessibility-compliance-accessibility-audit-v2