generate-mocs
Pass
Audited by Gen Agent Trust Hub on Mar 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill triggers subprocess calls to execute local Python scripts (
generate_concept_mocs.pyandgenerate_paper_mocs.py) and performs Git operations (add,commit,push) to synchronize vault changes. - [PROMPT_INJECTION]: The skill contains an indirect prompt injection surface (Category 8) because it ingests data from local configuration files that directly influence subsequent command-line execution and environment variables.
- Ingestion points: The skill reads
../_shared/user-config.jsonand../_shared/user-config.local.jsonto define variables likeVAULT_PATHandNOTES_PATH. - Boundary markers: No specific delimiters or safety instructions are present to prevent malicious data in the configuration files from altering agent behavior.
- Capability inventory: Includes file system reads, Python script execution, and Git network operations.
- Sanitization: No validation or sanitization of the configuration file content is performed before use in subprocess calls.
Audit Metadata