devops-engineer
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an inherent attack surface by ingesting and acting upon external data from Git repositories and CI/CD environments as part of its primary DevOps function.
- Ingestion points: The workflow processes repository content, commit metadata, and pipeline environment variables as shown in
references/scenarios.md. - Boundary markers: Explicit prompt delimiters or instructions to ignore embedded commands in external data are not defined in the provided instructions.
- Capability inventory: The skill is designed to execute powerful commands for cluster management (
kubectl) and repository updates (git) which are identified inreferences/scenarios.mdandreferences/workflow.md. - Sanitization: The examples rely on standard environment variable management and trusted commit metadata (
github.sha) for interpolation.
Audit Metadata