The Agent Skills Directory

[SAFE]: The skill's primary function is to help an agent shape raw markdown material into a structured article. It involves standard file reading and appending operations.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-provided content, which acts as a data ingestion surface. While malicious text in the input could attempt to influence the agent, the risk is mitigated by the skill's lack of network access and the 'disable-model-invocation' constraint. (1) Ingestion points: User-provided markdown file ('the pile'). (2) Boundary markers: Absent. (3) Capability inventory: File read and append tools only. (4) Sanitization: None described.
[COMMAND_EXECUTION]: The skill manages files using local file system tools for reading and appending. It does not perform arbitrary shell command execution, persistence, or privilege escalation.

writing-shape