The Agent Skills Directory

[SAFE]: The skill is a documentation-oriented tool that does not perform network operations, execute shell commands, or access sensitive system credentials. Its instructions are exclusively focused on generating markdown text from provided inputs.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from user-provided notes and conversation history, which creates a surface for indirect prompt injection. However, its capabilities are limited to producing a markdown concept brief, which significantly limits the risk of exploitation.
Ingestion points: SKILL.md defines inputs including user notes, conversation history, and repository context (README, issues).
Boundary markers: The instructions do not define delimiters or specific warnings to ignore embedded instructions in the ingested data.
Capability inventory: The skill is restricted to generating a structured Idea.md markdown file.
Sanitization: No explicit sanitization or filtering of input content is specified.

idea-md