memory-ingest
Fail
Audited by Snyk on Feb 28, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 1.00). The skill explicitly instructs the agent to "preserve the raw material verbatim" when creating notes and templates (write_note content), so any API keys, tokens, cookies, or passwords pasted into source inputs would be output unchanged, creating a direct exfiltration risk.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The workflow's Step 4 ("Research New Entities (Optional)") explicitly instructs performing brief web searches and the templates include external source URLs (e.g., "source: https://example.com/whitepaper.pdf"), so the agent may fetch and interpret public web content that can influence entity creation and follow-up actions.
Audit Metadata