operate-on-aws
Warn
Audited by Snyk on Nov 18, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The required OPERATE workflow (
investigate/create_release_readiness_review) has DevOps Agent read CloudWatch log lines and PR/repository source, which the skill itself notes "routinely contain text that users or third parties supplied", and outsiders can cause that text to appear in logs or PR content without the agent selecting a specific item.
MEDIUM W013: Attempt to modify system services in skill instructions.
- Attempt to modify system services in skill instructions detected (medium risk: 0.40). The skill directs the agent to create IAM roles, attach policies, and register an MCP server config in the user's cloud and editor, which are real state changes, but they are cloud-account and agent-config changes rather than machine or system-file changes, and every write is gated behind an explicit Yes.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W013
MEDIUMAttempt to modify system services in skill instructions.
Audit Metadata