toc-generator
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a guide for implementing tables of contents (TOC) using standard HTML and ARIA attributes. It does not include executable code, external dependencies, or network operations.
- [INDIRECT_PROMPT_INJECTION]: The skill advises the agent to read project context files (e.g.,
.claude/project-context.md) to understand content structure. - Ingestion points: Reads project context files and user-provided article content in
SKILL.mdunder the 'Initial Assessment' section. - Boundary markers: None explicitly defined in the skill instructions; relies on standard agent behavior.
- Capability inventory: The skill is limited to generating text-based output (TOC structures, HTML/ARIA snippets, and SEO checklists). It has no capabilities for file writing, command execution, or network communication.
- Sanitization: Standard LLM output sanitization applies; the skill instructions do not introduce new sanitization requirements as the output is descriptive.
Audit Metadata