The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from user-written story files, which creates a potential surface for indirect prompt injection if those files contain malicious instructions.
Ingestion points: The skill reads content from multiple project directories including characters/, chapters/, scenes/, and story-planning/, as well as files like summary.md and README.md.
Boundary markers: There are no explicit instructions or delimiters defined to separate user content from system instructions when these files are read into the agent's context.
Capability inventory: The skill utilizes the python3 interpreter to run analysis scripts, the grep utility for searching, and standard Read/Edit tools for file manipulation.
Sanitization: There is no evidence of sanitization or filtering of external narrative content before it is processed by the agent.
[COMMAND_EXECUTION]: The instructions direct the agent to execute local Python scripts via the shell to perform project analysis.
Evidence: The skill specifies command-line execution of timeline_tracker.py and consistency_checker.py located in the .claude/skills/storyboard-manager/scripts/ directory to generate markdown or JSON reports.

storyboard-manager