The Agent Skills Directory

[SAFE]: The skill does not contain any executable code or scripts. Its behavior is defined as an analytical process that involves reading local project documentation (.aidoc/profile.yaml and .aidoc/learnings.md) and generating draft text outputs.
[PROMPT_INJECTION]: The skill processes external data from project documentation files to decide what to draft. While this represents a surface for indirect prompt injection, the risk is mitigated by the fact that the skill's primary purpose is document analysis, it lacks autonomous execution capabilities, and it requires a human to review and act on all outputs.
Ingestion points: .aidoc/profile.yaml and .aidoc/learnings.md (identified in SKILL.md).
Boundary markers: None explicitly defined.
Capability inventory: File system read access to project documentation; text generation for drafting proposals.
Sanitization: No explicit sanitization of the input documentation is mentioned.

knowledge-extractor