recap

Fail

Audited by Snyk on Nov 17, 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 plain router, but its demo fallback runs unpinned code fetched from a GitHub repo via npx -y, which is risky without showing malicious intent.

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

  • Third-party content exposure detected (low risk: 0.10). The router itself reads only the user's input and local repo state, but its handoffs to recap-session (git history) and recap-topic (a topic that may require web research) can ingest outsider-authored text that the agent must actively select or that arrives via external contributors' commits, which is at most low exposure.

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

  • Potentially malicious external URL detected (medium risk: 0.30). The demo path falls back to npx -y github:Aboudjem/recap-studio demo, which fetches and executes code from an individual's GitHub repository (a personal, unofficial source with no strong first-party provenance or integrity pinning), so it is a real inbound runtime dependency at the common/reputable unofficial tier.

Issues (3)

E004
CRITICAL

Prompt injection detected in skill instructions.

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
CRITICAL
Analyzed
Nov 17, 2026, 12:03 PM
Issues
3