scientific-thinking

Warn

Audited by Snyk on Jul 29, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Potentially malicious external URL detected (high risk: 0.90). The skill's runtime "Update check" runs git remote commands and may run git -C <this-skill-dir> pull --ff-only, allowing upstream content (e.g. https://github.com/Agents365-ai/scientific-thinking-skill.git) to be fetched and overwrite SKILL.md and thus directly control agent instructions.

Issues (1)

W012
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 29, 2026, 04:13 PM
Issues
1
Security Audit — snyk — scientific-thinking