diagnosing-bugs
Fail
Audited by Snyk on Aug 12, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 0.80). The skill requires the agent to paste "one command" invocation and its output and explicitly endorses using curl / replaying captured traces or HARs, which can contain API keys, cookies, or other secrets and therefore may force the LLM to handle or output secrets verbatim.
Issues (1)
W007
HIGHInsecure credential handling detected in skill instructions.
Audit Metadata