ovstorage-contributor-verify-before-merge
Pass
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
Bashtool to executemaketargets (verify, test, validate-skills, verify-headers-clean) andgitcommands. These are standard operations for a developer tool intended to run verification gates on a local repository. - [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes data from
git statusandgit diffoutputs. This represents an attack surface where malicious instructions embedded in file changes could attempt to influence the agent's behavior. However, this is a standard risk for code analysis tools and is considered safe within the intended context of developer verification. - Ingestion points: Output from git commands and build tools in
SKILL.md. - Boundary markers: No explicit delimiters are used to wrap ingested data.
- Capability inventory: The skill has access to shell command execution (
Bash) and file reading (Read). - Sanitization: No sanitization or filtering of external tool output is implemented.
Audit Metadata