tao-validate-recipe-transfer
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [DYNAMIC_EXECUTION]: The
scripts/preprocess_parity.pyscript utilizesimportlib.import_module()to dynamically load and execute Python functions specified by the user through the--pathcommand-line argument. While this is the intended functionality to allow parity checks between different code implementations, it represents a dynamic code execution surface. - [INDIRECT_PROMPT_INJECTION]: The skill's scripts (
domain_gap_report.py,render_status.py,preprocess_parity.py) process external data formats such as JSON COCO annotations, YAML specifications, and JSON status reports. The output of these analyses is presented to the AI agent, creating a potential vector for indirect prompt injection if the source data files are manipulated to include malicious instructions. - Ingestion points: The skill ingests data in
scripts/domain_gap_report.py(COCO JSON),scripts/preprocess_parity.py(YAML/JSON preprocessing specs), andscripts/render_status.py(JSON status artifacts). - Boundary markers: The skill does not implement specific boundary markers or "ignore embedded instructions" warnings for the processed data.
- Capability inventory: The skill environment allows for bash execution and file modification tools.
- Sanitization: Content is parsed for structured data but is not sanitized to prevent natural language command interpretation by the LLM.
Audit Metadata