The Agent Skills Directory

[SAFE]: The skill consists of instructional guidelines for an agent to maintain chronological consistency in creative writing projects. No evidence of prompt injection, data exfiltration, or unauthorized command execution was found.
[INDIRECT_PROMPT_INJECTION]: The skill describes a workflow that ingests data from external markdown files. 1. Ingestion points: Event data is read from timeline/EVENT.md files. 2. Boundary markers: The skill does not define specific delimiters for untrusted content, but the context is limited to narrative planning. 3. Capability inventory: The skill references coordination with tools like canon-manager and causality-engine, but does not invoke arbitrary shell commands or network operations. 4. Sanitization: None mentioned, as the data is treated as story elements.

timeline