tao-generate-od-defects

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses subprocess.run to invoke model generation (generate.py) and pseudo-labeling (pseudo_label.py) scripts. These scripts are located within the /workspace/paidf-anomalygen directory of the official container image.
  • [EXTERNAL_DOWNLOADS]: Execution is tied to a specific, pinned NVIDIA container image (nvcr.io/nvidia/paidf-anomalygen:1.1.0). It also allows for optional Hugging Face model assets to be cached or downloaded from known repositories.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input data (testcases, recipes, and generation plans). It implements several defensive measures to mitigate injection or data corruption:
  • Ingestion points: Reads JSON, JSONL, and YAML files from user-specified input directories.
  • Boundary markers: Enforces strict schema validation for COCO and custom metadata formats.
  • Capability inventory: Subprocess calls are restricted to internal container scripts; file access is scoped to the provided input and output directories.
  • Sanitization: Uses yaml.safe_load for parsing, regex validation for dataset identifiers, and SHA256 hash verification for artifact integrity when a manifest is present.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 02:55 AM
Security Audit — agent-trust-hub — tao-generate-od-defects