confluence-docs-generator
Pass
Audited by Gen Agent Trust Hub on Aug 3, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local Python scripts (
scripts/scan_repo.py,scripts/find_endpoints.py, andscripts/validate_confluence_md.py) to automate codebase analysis. These scripts are implemented using the Python standard library, do not perform network requests, and include path resolution and validation logic to prevent directory traversal. - [INDIRECT_PROMPT_INJECTION]: The skill processes content from arbitrary codebases, which constitutes a surface for indirect prompt injection.
- Ingestion points:
scripts/scan_repo.py(directory structure and file names),scripts/find_endpoints.py(source code regex matching), and strategic reading of source files like READMEs, entry points, and controllers as defined inSKILL.md. - Boundary markers: The skill does not define explicit delimiters for codebase content but instructs the agent to sample files deliberately to bound context usage.
- Capability inventory: The skill allows for file reading, file writing (to a
docs/confluence/directory), and execution of the included Python scripts. - Sanitization: No specific sanitization or filtering of codebase content is mentioned before the information is processed by the agent, relying on the agent's internal safety filters.
Audit Metadata