technical-doc-creator
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input to generate HTML documentation and determine filenames, creating a vulnerability surface for XSS and directory traversal.
- Ingestion points: User-provided endpoint details, system names, and technical content in documentation requests defined in SKILL.md.
- Boundary markers: Absent; the skill does not instruct the agent to use delimiters or explicit warnings to prevent user-supplied data from being interpreted as code by browsers or the agent.
- Capability inventory: The agent is directed to use a file-writing capability to create a local HTML file named
[system]-docs.html. - Sanitization: Absent; the skill lacks instructions to escape HTML entities in the documentation content or to sanitize the
[system]variable used in the output filename to prevent directory traversal attacks.
Audit Metadata