workhuman-ci-integration

Pass

Audited by Gen Agent Trust Hub on Sep 11, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill promotes security best practices for CI/CD environments, focusing on preventing secret exposure in fork-triggered jobs and redacting sensitive data from artifacts.- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external repository files that could contain malicious instructions.
  • Ingestion points: Repository files including customer contracts, mapping digests, and synthetic fixtures are read using the Read, Glob, and Grep tools as specified in SKILL.md.
  • Boundary markers: The instructions lack specific delimiters or "ignore embedded instructions" warnings for the external data being processed.
  • Capability inventory: The agent has the ability to perform Write, Edit, and WebFetch operations based on its analysis of repository files.
  • Sanitization: Instructions focus on redacting sensitive output data but do not specify measures to sanitize input data against adversarial prompts.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 11, 2026, 10:05 AM
Security Audit — agent-trust-hub — workhuman-ci-integration