ov-ensure-coding-style
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes shell commands (
git diff,grep,tee) to programmatically identify files that have been modified compared to a reference upstream branch. These commands are standard for development workflows and are used here for their intended purpose of scoping the agent's tasks. - [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read external instructions from a local documentation file (
coding_style.md). This establishes a dependency on the content of that file to guide the agent's actions, which is a common pattern for project-specific automation. - Ingestion points:
../../../docs/dev/coding_style.md - Boundary markers: None specified; the agent is told to follow the file instructions exactly.
- Capability inventory: Shell command execution for git operations and file system interaction.
- Sanitization: None; the skill assumes the project documentation is a trusted source of instructions.
Audit Metadata