aws-cli
Warn
Audited by Snyk on Nov 21, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The required workflow is AWS CLI administration of the user's own account, but the CloudWatch log queries (
filter-log-events,logs tail --follow) read application logs that an outsider could influence by sending requests to a public Lambda function, so this is a low-risk path.
MEDIUM W013: Attempt to modify system services in skill instructions.
- Attempt to modify system services in skill instructions detected (low risk: 0.10). The skill documents available operations that change shared AWS infrastructure (terminating instances, editing security groups, creating IAM users and keys, updating Lambda code, and force-deleting buckets), so it passes the operational-change gate. It fails the irreversible-loss gate because no supplied text states that these operations cause unrecoverable loss of operational state; the "包括内容" and "删除目标多余文件" comments describe deletion but not irreversibility, so the tier is low.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W013
MEDIUMAttempt to modify system services in skill instructions.
Audit Metadata