The Agent Skills Directory

[SAFE]: No security threats detected. The skill's primary function is to process local creative assets (series and character bibles) into a structured episode card template.
[DATA_EXPOSURE_AND_EXFILTRATION]: The skill does not access sensitive environment variables, credentials, or system paths. It strictly interacts with project-specific documentation and does not contain any network-capable commands (e.g., curl, wget).
[REMOTE_CODE_EXECUTION]: No external dependencies, package managers, or remote script execution patterns are present. The workflow is restricted to text generation based on local templates.
[PROMPT_INJECTION]: Instructions are focused on content structure and creative boundaries. There are no attempts to bypass safety filters, extract system prompts, or override agent operational guidelines.
[COMMAND_EXECUTION]: The skill does not utilize any shell command execution or subprocess spawning. Its 'Stop Conditions' explicitly prevent the use of external media tools or video generation commands.
[INDIRECT_PROMPT_INJECTION]: While the skill ingests external data from series.md and characters.md, the lack of exploitable capabilities (such as file-system writes to sensitive areas or network exfiltration) renders this attack surface non-critical. The output is limited to markdown generation in a controlled subdirectory.

plotloom-episode-card