generating-documentation
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- PROMPT_INJECTION (LOW): Indirect Prompt Injection surface detected. The skill is designed to process external project data to generate documentation and automation scripts.
- Ingestion points: The skill ingests source code (processed via TSDoc in
tsdoc-examples.ts), project requirements, and architecture decisions to populate templates. - Boundary markers: The templates use standard Markdown and YAML boundaries, but there are no specific instructions or delimiters to prevent the agent from following instructions maliciously embedded in source code comments or ADR descriptions.
- Capability inventory: The skill has the capability to write files to the repository, including sensitive directories like
.github/workflows/, and generate shell scripts within those workflows. - Sanitization: No explicit sanitization or input validation logic is defined to filter malicious instructions from the data used to generate the documentation site or CI pipelines.
- EXTERNAL_DOWNLOADS (SAFE): The skill references standard and trusted documentation tools such as Docusaurus, MkDocs, and PlantUML. These references are part of the intended functionality for setting up a documentation environment and follow industry best practices.
Audit Metadata