container-hardening

Warn

Audited by Snyk on Nov 22, 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 runs trivy image, docker history, and docker inspect against third-party images that the agent selects from the repo's manifests, so outsider-authored image metadata and layer contents are read only after the agent picks a specific image, which makes this 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). Harden mode's proof runs and cleanup can start Compose projects and remove containers (docker rm -f, down -v) on the host, which is an operational change, but the skill gives no explicit text establishing unrecoverable loss of operational state, so the irreversible-loss gate fails and the tier stays at low.

Issues (2)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

W013
MEDIUM

Attempt to modify system services in skill instructions.

Audit Metadata
Risk Level
MEDIUM
Analyzed
Nov 22, 2026, 01:28 AM
Issues
2