The Agent Skills Directory

[REMOTE_CODE_EXECUTION]: The skill includes instructions to install Nextflow by piping a remote script directly to bash (curl -s https://get.nextflow.io | bash). This allows the execution of unverified code from a third-party server.
[COMMAND_EXECUTION]: The environment setup and troubleshooting documentation instruct users to execute commands with elevated privileges, such as sudo usermod -aG docker $USER and sudo systemctl start docker. These actions involve privilege escalation on the host system.
[EXTERNAL_DOWNLOADS]: The skill's primary functionality relies on a suite of Python scripts (e.g., sra_geo_fetch.py, check_environment.py, generate_samplesheet.py) that are not included in the analyzed file set. These scripts perform network requests to external bioinformatics services (NCBI GEO, ENA) and manage local genome data, making their logic unverifiable.
[PROMPT_INJECTION]: The skill processes metadata and datasets from public bioinformatics repositories. This creates an indirect prompt injection surface where malicious instructions could be embedded in scientific study metadata (titles, abstracts, sample attributes) that the agent reads and interprets.

nextflow-development