preflight
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill uses file paths from git diff output to determine which libraries to test, creating a dependency on untrusted metadata from the repository. * Ingestion points:
git diff --name-onlyoutput is processed to identify target libraries (SKILL.md). * Boundary markers: Absent; file paths are mapped directly to execution variables without delimiters. * Capability inventory: The skill executes shell commands viayarnandnx(SKILL.md). * Sanitization: No explicit sanitization of mapped library names or user-provided arguments is performed before shell interpolation. - [COMMAND_EXECUTION]: The skill executes local build and test commands using
yarnandnx. These operations are standard for the skill's intended purpose of running quality gates.
Audit Metadata