The Agent Skills Directory

[COMMAND_EXECUTION]: The skill includes instructions for environment validation using version check commands for Python modules and CLI tools. This is a standard practice for ensuring workflow reproducibility and compatibility.
[DATA_EXPOSURE_AND_EXFILTRATION]: Processes biological sequence data and metadata locally. No patterns for credential harvesting or exfiltration to external domains were identified.
[INDIRECT_PROMPT_INJECTION]: The skill ingests external data (FASTQ and metadata files). While it lacks explicit boundary markers for this data, the processing is constrained to scientific computation, presenting a low risk for prompt injection in this specific domain context.

microbiome-amplicon