docker-and-orchestration

Warn

Audited by Snyk on Nov 13, 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 relies on the agent doing "on-the-spot research" into stack requirements, base image digests, and security advisories (references/multi-stage-dockerfiles.md), which means searching and fetching arbitrary web pages where outsiders can publish text, but the agent must select those pages itself, so exposure is low rather than medium.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

  • Potentially malicious external URL detected (medium risk: 0.30). The only inbound source is the README's documented npx skills add install of this skill from an individually owned GitHub repository (racastellanosm/agent-skills), which is an unofficial but reputable-looking source for the skill's own installed material, so it is medium rather than no or high.

Issues (2)

W011
MEDIUM

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

W012
MEDIUM

Unverifiable external dependency detected (runtime URL that controls agent).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Nov 13, 2026, 03:31 PM
Issues
2