The Agent Skills Directory

[SAFE]: No malicious code, suspicious network activity, or obfuscation techniques identified. The skill operates within the expected parameters of a writing assistant.
[PROMPT_INJECTION]: Indirect prompt injection surface identified. The skill processes untrusted user-supplied dictation text which could contain malicious instructions. * Ingestion points: Pasted text via cleanup commands and file content read from disk. * Boundary markers: Absent; the skill does not define specific delimiters to isolate user data from instructions. * Capability inventory: file:read and file:write permissions allow the agent to process and save documents. * Sanitization: Absent; the skill instructions do not specify validation or sanitization of the dictation input.

dictation-cleanup