The Agent Skills Directory

[SAFE]: No evidence of malicious code, obfuscation, or unauthorized system access was found. The skill operates exclusively as a logical framework for text manipulation.
[PROMPT_INJECTION]: The skill processes external text for editing, creating a potential surface for indirect prompt injection. However, the limited capabilities (text rewriting) mitigate this risk. 1. Ingestion points: User-provided articles processed in SKILL.md during the splitting and rewriting stages. 2. Boundary markers: Absent; no delimiters are defined to isolate input text. 3. Capability inventory: Text analysis and rewriting; no network or shell capabilities are requested or used by the logic. 4. Sanitization: Absent; the skill does not include input filtering or validation.

edit-article