learn-investigate
Fail
Audited by Snyk on Jul 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 mandates collecting and appending file contents into evidence.ndjson (a "content" field) during investigation, which can force the LLM to output verbatim file data — including any embedded API keys/passwords — so it can exfiltrate secrets found in source files.
Issues (1)
W007
HIGHInsecure credential handling detected in skill instructions.
Audit Metadata