shipyard

Warn

Audited by Snyk on Nov 19, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (medium risk: 0.30). The required CI-worker path reads failed job logs and PR revisions from GitHub, and PR/issue content from outsiders can reach those logs and the task-source intake without the agent first choosing a specific item, so I scored this as medium under the recall-first rule, though the skill never names a monitored issue or PR feed.

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 documented npx skills@latest add itamaker/skills installation of the skill package, which is an instructed setup path whose content becomes installed skill material; the publisher is an individual/unestablished owner, not a verified first-party organization, so it is common/reputable unofficial and rated medium.

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 19, 2026, 07:13 AM
Issues
2