audit-decisions

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 transparent code-review audit with no malicious intent, but it instructs the agent to commit a notes file and edit the PR body, which alters the user's repository without being asked and conflicts with its own "leave the tree exactly as audited" rule, so under recall-first I rate it medium.

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

  • Third-party content exposure detected (medium risk: 0.30). The required workflow reads GitHub PR bodies and comments on each later pass, which are outsider-writable, to pick up banked ledger entries (the ledger lives in the PR body or a PR comment and "a later pass reads settled entries there").

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 16, 2026, 02:27 AM
Issues
2