commit-context
Fail
Audited by Snyk on May 20, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 0.90). This prompt directs the agent to call the agent memory HTTP endpoint with an Authorization: Bearer $AGENTMEMORY_SECRET header, which can lead the model to emit the secret verbatim in generated commands or requests (e.g., curl), creating an exfiltration risk.
Issues (1)
W007
HIGHInsecure credential handling detected in skill instructions.
Audit Metadata