explanatory-html-pages
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute a local Python script (
scripts/validate.py) to verify the semantic structure and self-containment of the generated HTML. This script uses only the Python standard library and performs no network or sensitive file system operations. - [INDIRECT_PROMPT_INJECTION]: The skill processes project-specific documentation and source files to generate explanatory content. While this creates a potential surface for instructions embedded in project files to influence the agent, the skill is scoped to generating static HTML content and includes validation steps to ensure no unexpected external dependencies are introduced.
- Ingestion points: Project context, documentation, and source files as defined in the input contract.
- Boundary markers: None explicitly defined in the instruction set.
- Capability inventory: Local file reading and execution of the included
validate.pyscript. - Sanitization: Relies on the provided
scripts/validate.pyto ensure output remains self-contained and free of external scripts or markers.
Audit Metadata