The Agent Skills Directory

[SAFE]: The skill facilitates the creation of technical documentation by reading and writing files in the .chalk/docs/engineering/ directory. It uses standard tools for file management and does not exhibit malicious behavior such as network exfiltration or command execution.
[INDIRECT_PROMPT_INJECTION]: There is a potential surface for indirect prompt injection because the skill reads existing documentation that could contain malicious instructions. Ingestion points: Documents in .chalk/docs/engineering/. Boundary markers: None. Capability inventory: Uses the Write tool to create markdown files. Sanitization: None. This finding is classified as safe because the capability is limited to document generation within the project context.

create-rfc