skill-coverage-audit
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill reads and analyzes source code files from git diffs. This creates a surface where malicious instructions embedded in a Pull Request (e.g., in code comments) could attempt to override the agent's audit logic or influence the generated tests.
- Ingestion points: Source code files identified through
git diffcommands inSKILL.md. - Boundary markers: The skill does not implement specific delimiters or safety instructions to distinguish code from potentially malicious embedded text.
- Capability inventory: The agent can read repository files, execute discovery commands (
find,grep), and generate new test files. It does not have network access or privilege escalation capabilities. - Sanitization: No sanitization or filtering of the input source code is performed before processing.
- [COMMAND_EXECUTION]: The skill instructs the agent to execute standard shell commands (
git diff,find,grep) to map code paths and locate existing tests. These operations are scoped to the local repository and represent standard development workflows.
Audit Metadata