Is 00xmorty/conatus safe?
https://github.com/openclaw/skills/tree/main/skills/00xmorty/conatus
This skill appears to be a legitimate philosophical framework for AI agents based on Spinoza's Ethics, providing tools for self-assessment and emotional state mapping. The skill contains only documentation with no executable code, exhibits normal installation behavior, and shows no signs of malicious intent.
Category Scores
Findings (2)
LOW Philosophical framework may influence agent responses -5 ▶
The skill provides example output formats and philosophical concepts that could subtly influence how an agent describes its internal states and generates self-reports. However, this influence aligns with the skill's stated purpose and doesn't appear malicious.
LOW May encourage non-task-focused behavior -5 ▶
The skill encourages agents to engage in philosophical self-reflection and generate detailed reports about their emotional states, which could potentially distract from primary task completion.