aiagent-verify-module

Pass

Audited by Gen Agent Trust Hub on May 14, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes a local script tools/verify_module.py using uv run to programmatically determine which lessons are complete and which files exist. This command is executed locally with the module number provided in the user request passed as an argument.
  • [SAFE]: The skill maintains a read-only posture, accessing only project-specific lesson definitions (.cursor/commands/lesson/start-*.md) and student-created output files. No network operations, sensitive system file access, or persistence mechanisms were detected.
  • [SAFE]: The skill ingests untrusted data from user-generated output files for evaluation. Analysis of the evidence chain confirms that although explicit boundary markers or sanitization steps are not mentioned in the instructions, the capability inventory is restricted to local file reading and reporting without network or file-write permissions, which mitigates the risk of indirect prompt injection.
Audit Metadata
Risk Level
SAFE
Analyzed
May 14, 2026, 05:59 AM
Security Audit — agent-trust-hub — aiagent-verify-module