NYC

build-pov-ray

Warn

Audited by Snyk on Feb 15, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 1.00). This skill explicitly instructs the agent to download and inspect source archives from public third-party locations (e.g., ftp://ftp.povray.org/pub/povray/ and archive mirrors via wget/curl), so it clearly ingests untrusted third‑party content as part of its workflow.

MEDIUM W013: Attempt to modify system services in skill instructions.

  • Attempt to modify system services in skill instructions detected (high risk: 1.00). The prompt explicitly instructs using sudo (e.g., "sudo cp ... /usr/local/bin" and "sudo make install") to write system-wide binaries, which requires elevated privileges and modifies system files, so it directs the agent to change the machine state with root access.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 09:24 PM