accessibility-patterns
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and analyze frontend code and HTML files, which are often provided by users or fetched from external, untrusted sources.
- Ingestion points: According to the
SKILL.mdfrontmatter, the skill triggers onfile-type:*.htmland frontend-related contexts. - Boundary markers: The instructions do not include specific delimiters or warnings to the agent to disregard potential instructions embedded in the HTML or code snippets being analyzed.
- Capability inventory: The skill is documentation-focused and does not implement any tools or scripts with capabilities for file writing, network exfiltration, or shell command execution.
- Sanitization: The skill does not provide mechanisms for sanitizing or escaping the content of the HTML files it processes.
Audit Metadata