The Agent Skills Directory

[Prompt Injection] (SAFE): The skill instructions focus strictly on documentation standards and do not contain patterns suggesting attempts to bypass AI safety guardrails or override system prompts.
[Data Exposure & Exfiltration] (SAFE): No credentials, sensitive file paths, or network requests were found. The skill does not interact with the filesystem or external APIs.
[Unverifiable Dependencies & RCE] (SAFE): The skill does not define or install any external Python or Node.js dependencies. It is a 'no-code' skill that relies on the agent's native text generation capabilities.
[Indirect Prompt Injection] (LOW): The skill ingests user-provided text to format it into documentation.
Ingestion points: User descriptions of processes provided at runtime.
Boundary markers: None explicitly defined in templates for input data.
Capability inventory: None. The skill generates text and does not have access to subprocesses, shell execution, or network tools.
Sanitization: None.
Risk: Extremely low as the agent has no dangerous tools to exploit even if malicious instructions are present in the documentation input.

sop-creator