The Agent Skills Directory

[SAFE]: The skill is composed entirely of markdown instructions and reference materials aimed at improving story structure. No executable scripts, command execution, or network communication patterns were identified.
[INDIRECT_PROMPT_INJECTION]: The skill manages plot state through external project files, which is a theoretical surface for indirect prompt injection if those files were to contain malicious instructions.
Ingestion points: mysteries/MYSTERY.md and knowledge/LEDGER.md (as referenced in SKILL.md).
Boundary markers: Absent; the skill does not define specific delimiters for separating plot data from instructions.
Capability inventory: None; the skill does not utilize any tools or functions that allow for network access, privilege escalation, or shell command execution.
Sanitization: Absent; there is no logic for sanitizing the content of the tracked files.

mystery-engine