The Agent Skills Directory

[PROMPT_INJECTION] (SAFE): The instructions in SKILL.md are focused on grounding the agent's responses in domain-specific reference material. There are no attempts to override system prompts or bypass safety filters.
[DATA_EXFILTRATION] (SAFE): No credentials or sensitive data access patterns were found. While references/validations.md contains filesystem path patterns (e.g., /home/[a-z]+/), these are used exclusively as regex patterns to detect (and discourage) hardcoded paths in user scripts.
[COMMAND_EXECUTION] (SAFE): Numerous shell commands for bioinformatics tools (BWA, GATK, samtools) are included in references/sharp_edges.md. These are clearly marked as educational examples ('WRONG' vs 'CORRECT') and are not intended for execution by the agent on the host system.
[REMOTE_CODE_EXECUTION] (SAFE): The skill does not perform any remote downloads or script execution. It references standard bioinformatics software that is expected to be present in a user's environment.

genomics-pipelines