super-agent

Fail

Audited by Snyk on Nov 18, 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 documented orchestration workflow with no concealment or pretext, but it lets the super agent rule on merge-gate holds and close parent issues without asking the owner, which is a self-granted action the user might not expect.

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

  • Third-party content exposure detected (medium risk: 0.30). The required workflow reads outsider-authored GitHub issue text (titles and comments) without the agent selecting an item: launch.sh reads each ticket's issue, intake.sh lists every open ready-for-agent issue of the active repos, and claim.sh reads the issue's comments.

Issues (2)

E004
CRITICAL

Prompt injection detected in skill instructions.

W011
MEDIUM

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

Audit Metadata
Risk Level
CRITICAL
Analyzed
Nov 18, 2026, 09:33 AM
Issues
2