The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute a local Python script helpers/python/pollinations_image_generator.py using a --prompt argument generated from user input. This creates a potential command injection vulnerability if the prompt is not sanitized for shell metacharacters.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted manuscript data to produce video prompts and scripts, posing a risk of indirect injection.
Ingestion points: Processes Manuscript Segment / Chapter, Story Arc & Hook, and Characters Involved inputs defined in SKILL.md.
Boundary markers: No specific delimiters or safety warnings for the AI to ignore instructions within the manuscript content are specified.
Capability inventory: The skill possesses the capability to execute shell commands via the python helper script.
Sanitization: There is no evidence of sanitization or escaping logic applied to user-supplied text before it is passed to the shell or integrated into prompts.

fiction-video-reels-director