The Agent Skills Directory

[SAFE] (SAFE): No security issues detected. The skill performs legitimate bioinformatics analysis using standard, well-known libraries.
[COMMAND_EXECUTION] (SAFE): No use of dangerous functions such as eval(), exec(), os.system(), or subprocess.run(). All logic is implemented using library-specific functions and standard Python control flow.
[DATA_EXFILTRATION] (SAFE): No network operations (e.g., requests, urllib, curl) were found. File operations are restricted to loading user-provided datasets and saving results to local directories derived from input names.
[EXTERNAL_DOWNLOADS] (SAFE): The skill does not attempt to download scripts or install packages at runtime. It relies on pre-installed scientific dependencies.
[CREDENTIALS_UNSAFE] (SAFE): No hardcoded API keys, tokens, or sensitive credentials were found in the scripts or documentation.
[PROMPT_INJECTION] (SAFE): The instructions in SKILL.md are descriptive and technical. No patterns attempting to bypass agent safety filters or override system instructions were identified.

single-cell-rna-qc