The Agent Skills Directory

[SAFE]: No security issues were identified. The skill defines a mechanical process for transcript cleanup through natural language instructions.
[NO_CODE]: The skill does not include any executable scripts, shell commands, tool definitions, or package dependencies. It is entirely instruction-based.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process raw transcripts, which represent a surface for untrusted data input.
Ingestion points: The skill processes text from a transcripts/ directory referenced in SKILL.md.
Boundary markers: The instructions do not define specific delimiters or boundary markers for the input data.
Capability inventory: There are no defined capabilities for command execution, network access, or file-writing outside of text generation within the agent's context.
Sanitization: No sanitization or filtering logic is provided for the input text.
Assessment: Due to the complete absence of exploitable tools or executable code, the risk of indirect prompt injection is negligible.

spoken-draft-cleanup