The Agent Skills Directory

[SAFE]: No malicious patterns or security risks were identified. The skill does not attempt to access credentials, perform network requests, or execute commands.
[NO_CODE]: The skill is composed entirely of Markdown documentation and YAML configuration files. It does not include any Python, Node.js, or shell scripts, eliminating the possibility of local code execution or dependency-related attacks.
[INDIRECT_PROMPT_INJECTION]: The skill provides a workflow for ingesting external data such as founder-supplied drafts and customer testimonials. It mitigates potential injection risks by instructing the agent to categorize inputs by evidence status (observed, inferred, proposed) and explicitly labeling missing information as unknown rather than inventing it. Furthermore, the absence of any tool-use capabilities prevents such data from triggering unintended system actions.

brand-positioning