circleci
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- Prompt Injection (SAFE): No instructions attempting to override agent behavior or bypass safety filters were detected.
- Data Exposure & Exfiltration (SAFE): No hardcoded secrets or sensitive file paths are accessed. Security-sensitive fields like 'AWS_ACCESS_KEY_ID' are used as placeholders for environment variables, which is a standard and safe practice.
- Unverifiable Dependencies & Remote Code Execution (SAFE): The skill references official CircleCI orbs (e.g., 'circleci/node', 'circleci/aws-cli'). While it describes the execution of a local script './deploy.sh', this is standard for CI/CD workflows and does not involve downloading untrusted remote scripts.
- Command Execution (SAFE): Command patterns for 'npm', 'docker', and 'kubectl' are provided as educational templates consistent with the primary purpose of the skill.
- Indirect Prompt Injection (LOW): As a documentation-based skill for CI/CD, it has a surface for generating configuration based on user input. However, it does not ingest external untrusted data directly at runtime, and the risk is considered low and typical for this category of developer tool.
Audit Metadata