The Agent Skills Directory

[SAFE]: No malicious patterns detected. The skill provides a structured methodology for product analysis and uses standard agent features for local state management.
[INDIRECT_PROMPT_INJECTION]: The skill has a data ingestion surface through user-provided descriptions of their projects and experiences. It includes a memory persistence capability where results are stored in 'config.paths.memory'. However, this is consistent with the skill's primary purpose, and there are no high-privilege capabilities (such as network access or shell command execution) that could be exploited through this surface. Evidence chain: 1. Ingestion points: User input describing resources or projects (SKILL.md); 2. Boundary markers: Absent; 3. Capability inventory: Writes to config.paths.memory (SKILL.md); 4. Sanitization: Absent.

zmm-product