infographic

Fail

Audited by Snyk on Feb 16, 2026

Risk Level: HIGH
Full Analysis

HIGH W007: Insecure credential handling detected in skill instructions.

  • Insecure credential handling detected (high risk: 1.00). This skill explicitly instructs the agent to preserve and embed "all source data verbatim" (including "Data Points (Verbatim)" and all text labels) into generated files and image-generation prompts, so any secrets present in the provided content would be copied into the LLM's outputs.

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

  • Third-party content exposure detected (high risk: 0.90). The skill explicitly ingests arbitrary user-provided source content ("If user pastes content: save to source.md" and "Read the entire document thoroughly" in Step 1) and preserves/verbatim-uses that content in analysis and prompt generation, so untrusted third-party/user-generated text can be read and incorporated into the agent's workflow.
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 16, 2026, 12:21 AM