intake

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The prompt requires embedding the raw signal's "useful information" into a GitHub Issue, which could force the model to output any secrets present in that raw signal verbatim (risking exfiltration).

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The skill explicitly instructs sending raw signal data to GitHub (creating an unlabeled issue and returning its URL), which is a direct data-exfiltration pattern and can leak sensitive information.