The Agent Skills Directory

[SAFE] (SAFE): No malicious patterns, obfuscation, or exfiltration vectors were detected. The skill's behavior is consistent with its stated purpose of content generation assistance.- [NO_CODE] (SAFE): The skill does not contain any Python, Node.js, or shell scripts. It relies entirely on natural language instructions for the AI agent.- [Indirect Prompt Injection] (LOW): The skill ingests user-provided topics as data. However, since the skill has no 'capability tier' (no network access, no file system writes, and no command execution), the risk of exploiting the agent via external data is negligible. Mandatory evidence: 1. Ingestion points: User input for topic preferences (SKILL.md). 2. Boundary markers: None present. 3. Capability inventory: None (no scripts or tools). 4. Sanitization: None present.

topic-generation