The Agent Skills Directory

[SAFE]: The skill operates entirely locally using Python standard libraries. No unauthorized network access, data exfiltration, or persistence mechanisms were found. The scripts included (parse_requirements.py and estimate_tasks.py) use standard libraries like argparse, csv, and re to process local files.
[PROMPT_INJECTION]: The skill processes untrusted external data, such as requirement documents and task lists, creating an indirect prompt injection surface. The risk is low as the processing is restricted to text parsing and markdown generation. * Ingestion points: scripts/parse_requirements.py (reads requirement files) and scripts/estimate_tasks.py (reads task CSV/text files). * Boundary markers: Absent; there are no explicit delimiters or instructions to ignore embedded commands in the processed data. * Capability inventory: The skill can read local files and execute its own internal scripts; it does not have network access or advanced system permissions. * Sanitization: None detected; the scripts utilize regular expressions for extraction but do not validate the content against malicious instructions.

project-manager-senior