The Agent Skills Directory

[SAFE]: No malicious patterns such as data exfiltration, remote code execution, or obfuscation were found in the provided files. The skill operates within a restricted local environment using standard file system tools for its intended creative purpose.
[COMMAND_EXECUTION]: The skill utilizes the ls command to list files in the script/ directory. This is a standard operation used to track episode history and ensure narrative consistency and is correctly scoped to the script-related path.
[PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it reads existing files from the script/ directory to maintain continuity. This is a core functional requirement for the skill's purpose.
Ingestion points: Reads existing script files from the script/ folder as instructed in SKILL.md.
Boundary markers: None explicitly defined in GUIDELINES.md or SKILL.md to distinguish between instructions and data.
Capability inventory: Authorized tools include Read, Write, and Bash (ls) as defined in SKILL.md frontmatter.
Sanitization: No specific sanitization or filtering of ingested content is mentioned in the provided documentation.

scriptwriter-skill