The Agent Skills Directory

[SAFE]: No security threats were detected in the analyzed files. The skill is designed as a conversational logic tool for psychological analysis based on Robert Cialdini's book 'Influence'.
[NO_CODE]: The skill does not include any executable scripts, shell commands, or external dependencies. It relies solely on natural language processing within the agent's context.
[DATA_EXPOSURE_AND_EXFILTRATION]: There are no requests for sensitive data, environment variables, or network access. The skill operates exclusively on the information provided by the user in the prompt.
[PROMPT_INJECTION]: The instructions do not contain any patterns attempting to bypass safety guardrails, override system prompts, or exfiltrate configuration data.
[INDIRECT_PROMPT_INJECTION]: While the skill processes user-supplied scenarios, it lacks the necessary capabilities (such as file-writing or command execution) to be exploited via indirect injection.

contrast-principle