cicd-hardening
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external data such as CI/CD workflow files and pull request metadata. * Ingestion points: CI/CD configuration files (e.g., .github/workflows/*.yml) and pull request titles or descriptions. * Boundary markers: There are no instructions for using delimiters to separate untrusted data from the agent's instructions. * Capability inventory: The skill enables the agent to interpret complex configuration logic to generate security assessments. * Sanitization: The skill does not describe methods for sanitizing or escaping the data retrieved from external sources before it is processed.
Audit Metadata