meticulous-simulate-and-diff

Warn

Audited by Snyk on Mar 26, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.90). The skill instructs running a simulation against an appUrl (a live/original recorded URL) and explicitly directs the agent to read the saved page HTML in ~/.meticulous/replays//screenshots/*.metadata.json (the before.dom fields) to analyze diffs, which are untrusted third‑party page contents the agent must interpret.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 26, 2026, 05:54 PM
Issues
1