ov-ensure-coding-style
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands, including
git diff,grep, andtee. It also instructs the agent to follow command-based instructions exactly from an external file (coding_style.md). - [INDIRECT_PROMPT_INJECTION]: The skill relies on instructions from
../../../docs/dev/coding_style.mdand user-provided branch names to determine its actions. If these sources are manipulated, the agent may execute unintended commands. - Ingestion points: The skill reads
../../../docs/dev/coding_style.mdand accepts user input for<ref_branch>and CMake targets in SKILL.md. - Boundary markers: There are no explicit boundary markers or instructions to treat the external file content as untrusted data or to ignore embedded instructions.
- Capability inventory: The skill uses shell command execution (
git,grep,tee) and expects to use system build/linting tools. - Sanitization: The skill does not validate or sanitize the
<ref_branch>or CMake target inputs before they are used in shell command contexts.
Audit Metadata