wcag3-preview
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill includes a 'Delta Analysis Mode' that processes user-provided accessibility audit reports. This ingestion point represents a surface for indirect prompt injection, as malicious instructions could be embedded within the report data. However, the risk is significantly mitigated by the skill's lack of dangerous capabilities (such as network access, file system modifications, or command execution).
- Ingestion points: The agent is instructed to 'Read the audit report' in the Delta Analysis Mode section of
SKILL.md. - Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore embedded commands within the ingested data.
- Capability inventory: No subprocess calls, network operations, or file-writing tools are defined in the provided files.
- Sanitization: There are no instructions for sanitizing or validating the contents of the audit reports before processing.
Audit Metadata