image-management
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 only outsider-facing text path is
docker search nginx(line 28), which queries the public Docker Hub registry, whose image descriptions are community-authored, but the agent must actively run this search and the skill does not make it part of a required workflow.
MEDIUM W013: Attempt to modify system services in skill instructions.
- Attempt to modify system services in skill instructions detected (medium risk: 0.30). The skill documents operational changes to the Docker host (persistent registry container via
docker run -d, anddocker system prune --volumes, which irreversibly deletes unused volumes with no recovery guidance), but the host's scope is not established as shared, so the result is medium rather than high.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W013
MEDIUMAttempt to modify system services in skill instructions.
Audit Metadata