earth2studio-create-prognostic

Fail

Audited by Snyk on Jul 22, 2026

Risk Level: CRITICAL
Full Analysis

CRITICAL E005: Suspicious download URL detected in skill instructions.

  • Suspicious download URL detected (high risk: 0.80). One URL (https://github.com/198808xc/Pangu-Weather) points to a third‑party GitHub repository owned by an unfamiliar/random‑looking username, which is a high‑risk indicator for untrusted executable or model distribution.

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

  • Third-party content exposure detected (high risk: 0.75). The required workflow ingests outsider-authored free text via Step 0 (“Please provide a reference inference script URL/path”), which may point to arbitrary external content that the agent then loads and places into the LLM context for matching/creation.

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

  • Potentially malicious external URL detected (high risk: 0.90). The SKILL.md example (SKILL.md:219) explicitly shows the agent fetching an external inference script from https://github.com/198808xc/Pangu-Weather at runtime ("fetches inference.py"), which would bring remote code/content into the agent execution path and be used to drive the wrapper implementation.

Issues (3)

E005
CRITICAL

Suspicious download URL 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
Jul 22, 2026, 08:00 AM
Issues
3
Security Audit — snyk — earth2studio-create-prognostic