diagnosing-bugs
Fail
Audited by Snyk on Jul 7, 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 explicitly instructs the agent to paste the exact command invocation and its output (including curl/HTTP invocations), which could contain API keys, tokens, cookies or passwords and therefore may force the LLM to emit secrets verbatim.
Issues (1)
W007
HIGHInsecure credential handling detected in skill instructions.
Audit Metadata