The Agent Skills Directory

[SAFE]: The skill operates as a document editor, reading raw material files and writing prose to a specified article file. All behaviors are within the scope of its stated purpose and confined to local text processing.
[PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it processes untrusted content from user-provided notes and codebase maps. 1. Ingestion points: 'the pile' markdown file and 'codebase-map-understand.md' (SKILL.md). 2. Boundary markers: Absent. 3. Capability inventory: Reading and writing local files; no shell execution or network access. 4. Sanitization: Absent. This risk is assessed as safe because the skill lacks exploitable capabilities like internet access or command execution.

writing-shape