skills/meisijiya/skills/test-guard/Gen Agent Trust Hub

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 Bash tool to run git grep and grep for identifying specific patterns within the project's test/ and src/ 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 diff in the CI integration pattern. 2. Boundary markers: Absent; the skill reads file content without explicit delimiters or warnings against embedded instructions. 3. Capability inventory: Utilizes Read, Bash (for grep-based audits), and Glob tools. 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-router plugin, which aligns with the skill author's identifier.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 10, 2026, 08:13 AM
Security Audit — agent-trust-hub — test-guard