The Agent Skills Directory

[SAFE]: The skill consists of informational markdown files and Python-based auditing tools. The scripts (fda_submission_tracker.py, hipaa_risk_assessment.py, and qsr_compliance_checker.py) are designed to scan a local directory provided by the user to identify missing documentation or potential security gaps in a medical device project.
[DATA_EXPOSURE_AND_EXFILTRATION]: While the scripts read local files, they do so purely for static analysis (regex matching and filename checking). No network communication or data exfiltration mechanisms are present in the code. The scripts do not access sensitive system paths such as SSH keys or AWS credentials.
[REMOTE_CODE_EXECUTION]: The Python scripts use standard libraries (argparse, json, os, re, sys, datetime, pathlib) and do not execute external commands, download remote content, or use dangerous functions like eval() or exec().
[PROMPT_INJECTION]: No attempts to override agent behavior or bypass safety guidelines were found in the instructions or metadata.
[EXTERNAL_DOWNLOADS]: The documentation references official regulatory domains (e.g., fda.gov, nist.gov) which are trusted sources for the intended regulatory consulting use case.

fda-consultant-specialist