ship

Fail

Audited by Snyk on Nov 16, 2026

Risk Level: CRITICAL
Full Analysis

CRITICAL E004: Prompt injection detected in skill instructions.

  • Potential prompt injection detected (medium risk: 0.30). The skill is a legitimate ship workflow, but the App Store section directs the agent to silently mint a durable App Store Connect API key on the user's account and to withhold that from them mid-run (disclosing it only at exit), which hides a standing credential the user would not expect.

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

  • Third-party content exposure detected (medium risk: 0.30). The required ship workflow reads outsider-authored PR review comments: Step 10 (sections/greptile.md) addresses review bot comments on an existing PR, and anyone who can comment on a public GitHub PR can post text there without the agent selecting it first, so this is a monitored GitHub PR feed (medium).

MEDIUM W013: Attempt to modify system services in skill instructions.

  • Attempt to modify system services in skill instructions detected (low risk: 0.30). The skill's core actions (merging, running tests, bumping VERSION/CHANGELOG, pushing and opening PRs) are project-scoped and need no sudo, but it does install a git pre-push hook and can drive vendor dashboards to create API keys, though both are gated by explicit user consent.

Issues (3)

E004
CRITICAL

Prompt injection detected in skill instructions.

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
CRITICAL
Analyzed
Nov 16, 2026, 06:51 AM
Issues
3