circleci-cli
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- Command Execution: The skill is designed to execute local
circleciCLI commands to inspect, validate, and mutate pipeline states. This is the intended primary functionality of the skill, and it includes guidelines to prioritize read-only diagnostics before performing mutating actions. - Indirect Prompt Injection: The skill processes output from external command executions, such as pipeline logs or configuration validation results, which introduces a potential surface for indirect instructions to be ingested into the agent context.
- Ingestion points: Output generated by the
circleciCLI commands (SKILL.md). - Boundary markers: The instructions do not define specific delimiters or "ignore" instructions for the ingested CLI output.
- Capability inventory: The skill can perform mutating actions such as rerunning jobs and triggering pipelines based on the gathered data.
- Sanitization: No specific sanitization or filtering of the CLI output is described in the workflow.
Audit Metadata