test-guard
Pass
Audited by Gen Agent Trust Hub on Aug 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
Bashtool to rungit grepandgrepfor identifying specific patterns within the project'stest/andsrc/directories. Examples include searching for skipped tests and mocking patterns:git grep -nE '\\b(skip|...)\\b' test/. - [PROMPT_INJECTION]: The skill processes untrusted test files from pull requests, creating an indirect prompt injection surface. 1. Ingestion points: Source code and test files identified via
git diffin the CI integration pattern. 2. Boundary markers: Absent; the skill reads file content without explicit delimiters or warnings against embedded instructions. 3. Capability inventory: UtilizesRead,Bash(for grep-based audits), andGlobtools. 4. Sanitization: Absent; the skill does not filter or sanitize the contents of the audited files. - [SAFE]: The skill references a vendor-specific resource, the
meisijiya-review-routerplugin, which aligns with the skill author's identifier.
Audit Metadata