deepagents-skills
Warn
Audited by Snyk on Aug 16, 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 example performs a runtime fetch of "https://raw.githubusercontent.com/.../SKILL.md" and injects the fetched SKILL.md text into the agent's store, meaning remote content can directly control the agent's instructions.
Issues (1)
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata