semantic-recall
Fail
Audited by Snyk on Apr 29, 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 requires returning raw, verbatim snippets (from workspace files or Pinecone record metadata) without summarization or redaction, so any API keys/passwords present in those snippets would be included in the LLM's output, enabling secret exfiltration.
Issues (1)
W007
HIGHInsecure credential handling detected in skill instructions.
Audit Metadata