scan-and-fix-accessibility
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external websites via the
startAccessibilityScantool to identify accessibility violations.\n - Ingestion points: Webpage content and scan reports retrieved by the
startAccessibilityScantool as described in SKILL.md.\n - Boundary markers: The instructions do not define specific delimiters or provide warnings to the agent to ignore potentially malicious instructions embedded in the scanned webpage content.\n
- Capability inventory: The skill is designed to generate code snippets and invoke specific accessibility tools; no arbitrary command execution, network exfiltration of local files, or unauthorized file system access is defined.\n
- Sanitization: There is no evidence of sanitization, escaping, or validation performed on the webpage content before it is processed by the agent.
Audit Metadata