response-compliance

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The document includes examples that pass API keys directly on the command line (e.g., --api-key 1 and --api-key lb-xxxxxxxxxxxxxxxx) which encourages embedding secret values verbatim in generated commands/outputs, creating a high exfiltration risk.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The compliance test script clones and runs the remote repository https://github.com/openresponses/openresponses at runtime (into scripts/openresponses-compliance/) and executes its CLI test runner, meaning fetched remote code is executed and relied upon.