The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute a shell command to read internal state files.
Evidence: The 'Memory Protocol' section in SKILL.md mandates the execution of cat .claude/context/memory/learnings.md at the start of the session.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes external code files without explicit sanitization or boundary markers.
Ingestion points: The skill operates on Python scripts matching the glob **/dask_analysis/*.py via the Read tool.
Boundary markers: No delimiters or instructions to ignore embedded commands are present in the processing logic.
Capability inventory: The agent is granted Read, Write, and Edit tools, which could be abused if malicious instructions are encountered in the data.
Sanitization: No evidence of validation or filtering for the content of the scripts being analyzed.
[COMMAND_EXECUTION]: The skill encourages the use of distributed computing clusters which involves spawning new processes or connecting to remote schedulers.
Evidence: 'Iron Law' #5 and the 'Anti-Patterns' section in SKILL.md explicitly direct the agent to implement dask.distributed.Client and LocalCluster().

large-data-with-dask