detect-bullshit-tests

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill instructs the agent to read targeted test files in full and "quote the offending line in the finding" (and include file:line with the offending assertion), which forces verbatim reproduction of file lines and could expose any embedded secrets (API keys/passwords) present in tests.