creating-skill
Warn
Audited by Snyk on Aug 26, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.70). The file references/agent-skill-specification.md explicitly instructs fetching external documentation at runtime ("Fetch the complete documentation index at: https://agentskills.io/llms.txt"), meaning external content could be loaded into the agent's context and thus directly influence prompts/instructions.
Issues (1)
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata