fixing-accessibility
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external HTML files to identify accessibility violations, which creates a surface where malicious instructions embedded in those files could attempt to influence the agent's behavior. However, the risk is negligible as the skill lacks any execution capabilities or tool access.\n
- Ingestion points: The skill accepts a
<file>argument for review inSKILL.md.\n - Boundary markers: No explicit delimiters or instructions to ignore embedded commands within the analyzed files are provided.\n
- Capability inventory: The skill is limited to reporting and proposing code changes; it does not utilize subprocess calls, network access, or file-writing tools.\n
- Sanitization: No sanitization or validation of the input file content is specified.
Audit Metadata