project-planner
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill includes two Python scripts,
scripts/generate_project_docs.pyandscripts/validate_documents.py, which are intended for local execution to facilitate document creation and checking. - [INDIRECT_PROMPT_INJECTION]: The document generation process takes user-supplied strings and interpolates them into markdown templates, creating a persistence surface for potentially malicious content that could affect other agents processing these documents.
- Ingestion points: User-provided inputs for project name, features, and components via command-line arguments in
scripts/generate_project_docs.py. - Boundary markers: None implemented in the generated documentation files.
- Capability inventory: The skill uses standard file system write operations to save the generated documentation.
- Sanitization: No validation or sanitization is performed on the user-supplied strings before they are written to the templates.
Audit Metadata