The Agent Skills Directory

[SAFE]: The skill consists of text-based instructions for organizing film production data into a CSV format. No executable code or suspicious patterns are present.
[INDIRECT_PROMPT_INJECTION]: The skill processes external data (shot briefs and contracts). While it lacks explicit boundary markers for this untrusted data, the agent's capabilities are limited to local file operations, and it is configured with 'disable-model-invocation: true', significantly reducing the risk of exploitation.
Ingestion points: Reads all shot briefs in scope and the core contract (SKILL.md).
Boundary markers: Absent.
Capability inventory: File read and File write within the project directory.
Sanitization: Absent.

shot-list