The Agent Skills Directory

[SAFE]: No malicious patterns or high-risk behaviors were detected. The skill primarily functions as a prompting template for communication style refinement.- [INDIRECT_PROMPT_INJECTION]: The skill references local documentation files, which constitutes a surface for indirect prompt injection, though the risk is negligible due to the lack of executable capabilities.
Ingestion points: CONTEXT.md and CONTEXT-MAP.md (referenced in SKILL.md).
Boundary markers: Absent; the skill does not define specific delimiters for the context retrieved from these files.
Capability inventory: None. The skill explicitly disables tool use via disable-model-invocation: true and includes no scripts or subprocess calls.
Sanitization: Absent; the skill relies on natural language processing of the documentation content.

wait-what