ov-transformation-tests
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to build and run unit tests. This is a standard and expected functional requirement for a skill designed to assist with software development and testing within the OpenVINO toolkit.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests instructions from a local documentation file (
src/common/transformations/docs/writing_tests.md). While reading external content can theoretically introduce indirect instructions, the file is a local project resource intended for guiding the agent's task. - Ingestion points:
SKILL.md(Step 1 references the local documentation file). - Boundary markers: None explicitly mentioned in the skill body.
- Capability inventory: The skill performs file reads, code writing, and command execution (build/run tests).
- Sanitization: Not applicable as the input is internal project documentation.
Audit Metadata