shared-validation-rule

Pass

Audited by Gen Agent Trust Hub on Jun 23, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill defines a verification workflow that uses shell commands to automate unit testing. These commands utilize 'node' to extract package information and 'npm' to execute tests within a specific workspace.
  • Evidence: The 'Verification' section in 'SKILL.md' contains bash instructions such as 'npm run test --workspace "$SHARED_PKG" -- --runInBand --runTestsByPath "packages/shared/test/validation/rules/.rule.test.ts"'.
  • [DATA_INGESTION_VULNERABILITY]: The skill processes user-supplied inputs (rule names, parameters, and examples) to generate source code and test files. While this creates a surface for potential indirect prompt injection, the skill includes built-in mitigations.
  • Evidence: The skill takes several inputs from the user to define the rule's logic and identity.
  • Sanitization: The instructions explicitly mandate the normalization of the rule name to 'kebab-case' before use in file paths or shell commands, effectively sanitizing input and preventing common command injection or path traversal attacks.
  • Capability Inventory: The agent has the capability to write files to the 'packages/shared' directory and execute the verification commands provided in the documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 23, 2026, 04:47 PM
Security Audit — agent-trust-hub — shared-validation-rule