pro-zh-summary
Warn
Audited by Snyk on Mar 6, 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 calls transformers.from_pretrained("heack/HeackMT5-ZhSum100k") at runtime, which fetches external model/tokenizer artifacts (heack/HeackMT5-ZhSum100k) that are required for operation and directly determine the agent's generated prompts/responses.
Audit Metadata