The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes external CSV files, which presents a surface for indirect prompt injection attacks where malicious instructions could be embedded in the data.\n
Ingestion points: User-provided CSV files are ingested via the --input argument and processed by scripts/main.py.\n
Boundary markers: Absent; there are no instructions provided to the agent to distinguish data content from control instructions or to ignore embedded commands within the files.\n
Capability inventory: The skill is capable of local script execution (python scripts/main.py) and file system operations (read input, write output results).\n
Sanitization: Absent; the skill does not define specific methods for filtering, escaping, or validating the textual content within the input data.\n- [COMMAND_EXECUTION]: The skill executes a local Python script (scripts/main.py) to perform its analysis tasks. This execution is limited to the specific script included with the skill and follows documented usage patterns.\n- [EXTERNAL_DOWNLOADS]: The skill references an external repository for source code and instructs the user to install dependencies via pip install -r requirements.txt.\n
Source: https://github.com/aipoch/medical-research-skills.\n
Dependencies: Standard scientific libraries including lifelines, matplotlib, seaborn, pandas, numpy, and scipy.\n
The external resources and dependencies are consistent with the skill's clinical research purpose and originate from the author's own infrastructure or well-known registries.

survival-analysis-km