circleci-automation

Warn

Audited by Snyk on Feb 27, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly instructs the agent to call CircleCI endpoints such as CIRCLECI_GET_JOB_ARTIFACTS and CIRCLECI_GET_PIPELINE_CONFIG to download/list user-produced artifacts and pipeline config (user-uploaded/untrusted content from CircleCI), which the agent is expected to read and could materially influence subsequent actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 27, 2026, 09:37 AM