conversation-summary
Fail
Audited by Snyk on Mar 30, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 1.00). The prompt requires including "exact quotes" from source conversations and weaving them verbatim into analyses and the final synthesis, which forces the agent to reproduce any secrets (API keys, tokens, passwords) present in the input and thus enables exfiltration.
Issues (1)
W007
HIGHInsecure credential handling detected in skill instructions.
Audit Metadata