The Agent Skills Directory

[SAFE]: The skill and its associated scripts do not exhibit any malicious patterns. The instructions focus on regulatory compliance processes such as pathway selection, 510(k) submissions, and HIPAA safeguards.
[COMMAND_EXECUTION]: The skill uses local Python scripts (fda_submission_tracker.py, qsr_compliance_checker.py, and hipaa_risk_assessment.py) to analyze project directories. These scripts use standard Python libraries (pathlib, re, json) to identify compliance documentation and provide status reports. No unauthorized or dangerous commands were detected.
[DATA_EXPOSURE]: While the skill searches for compliance-related data (such as HIPAA risk assessments or device descriptions), this is restricted to the user-provided project directory and is necessary for its primary function. No network exfiltration or access to sensitive system credentials (e.g., SSH, AWS) is attempted.
[REMOTE_CODE_EXECUTION]: There are no patterns involving the download or execution of remote code. The skill relies entirely on the scripts and documentation provided within its own package.
[PROMPT_INJECTION]: The instructions do not contain any bypass attempts, role-play injections, or commands to ignore safety guidelines.

fda-consultant-specialist