tao-analyze-gaps-od-map
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute Docker commands and a Python validation script (scripts/verify_object_detection_spec.py) to perform gap analysis and validate configurations.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external annotation data (KITTI or COCO format), creating an attack surface for indirect prompt injection. Ingestion points: The skill reads ground-truth and inference annotation paths. Boundary markers: None present. Capability inventory: The skill executes Docker containers and writes results to directories. Sanitization: The skill uses
yaml.safe_load()and specific value validation in its verification script to mitigate risks from malformed configuration files.
Audit Metadata