aws-cloudwatch
Warn
Audited by Snyk on Jul 27, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.65). SKILL.md:13-47 shows the workflow running CloudWatch Logs Insights where the user-supplied
--query-stringand resulting log@message/fieldsare ingested from AWS into the agent-side execution (and thus into the LLM-visible context when results are returned); AWS log contents are outsider-authored text (not chosen by the operating user as their own input).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata