The Agent Skills Directory

[SAFE]: The skill and its associated scripts perform localized analytical tasks such as decision scoring and stakeholder mapping without any network operations or sensitive file access.
[COMMAND_EXECUTION]: The skill references two internal Python scripts (scripts/decision_matrix_scorer.py and scripts/stakeholder_mapper.py). These scripts use standard Python libraries (json, sys, argparse, typing) to process data and generate reports. No arbitrary command execution or unsafe subprocess calls were detected.
[INDIRECT_PROMPT_INJECTION]: While the skill processes user-provided content (plans, decisions, agendas) as part of its core functionality, it lacks any high-risk capabilities (such as network exfiltration or file system modifications) that could be leveraged for an attack. The analytical nature of the tools serves as a benign processing layer.

executive-mentor