ov-transformation-tests

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to build and run tests locally. While this involves shell command execution, it is consistent with the skill's primary purpose of unit testing in a development environment.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes content from a local documentation file to guide its actions, which represents a potential surface for indirect prompt injection if that file were maliciously modified.
  • Ingestion points: The agent reads the documentation file located at src/common/transformations/docs/writing_tests.md.
  • Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat the documentation file content as data rather than instructions.
  • Capability inventory: The skill possesses capabilities to write files and execute build/run commands.
  • Sanitization: No sanitization or validation of the documentation content is performed before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 04:26 PM
Security Audit — agent-trust-hub — ov-transformation-tests