packages
Warn
Audited by Snyk on Jun 22, 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). The skill’s runtime workflow runs
aiwg packages list/info, which returns metadata including “source URL” and “full metadata” for Git-sourced packages; that metadata is derived from repositories installed viaaiwg install(i.e., outsider-authored content from third-party Git repos) and is then summarized/printed into the agent’s LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata