The Agent Skills Directory

[NO_CODE]: The skill consists entirely of Markdown files and documentation templates. There are no Python, Node.js, or shell scripts included in the package.- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to process documents from an uploads/ directory to summarize patterns and update a memory.md file. While this is a data ingestion surface, the risk is mitigated by the lack of high-privilege tools. * Ingestion points: User-provided files in the uploads/ directory. * Boundary markers: Not specified in the instructions. * Capability inventory: Limited to file reading and writing within the skill directory; no network or shell capabilities are present. * Sanitization: No explicit sanitization or filtering logic is defined for the uploaded content.- [SAFE]: All external URL references are for attribution purposes and target well-known services (e.g., x.com). These links do not involve automated downloads or remote code execution.

ceo-personal-os