mamba-architecture
Warn
Audited by Snyk on Mar 28, 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). The SKILL.md explicitly instructs loading pretrained models and tokenizers from public HuggingFace repos (see "Load from HuggingFace" where AutoTokenizer.from_pretrained and MambaLMHeadModel.from_pretrained are used), which are untrusted third‑party artifacts the agent would ingest and which can materially change its outputs/behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata