The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes untrusted user-provided content which presents a surface for indirect prompt injection. \n- Ingestion points: The skill ingests user-provided text files and articles (e.g., article.md) as specified in the workflow in SKILL.md. \n- Boundary markers: No delimiters or instructions are specified to help the agent distinguish user-provided content from its own instructions or to ignore embedded prompts. \n- Capability inventory: The skill has access to Bash, Read, Write, and Edit tools, which provide a functional surface for file manipulation and command execution if exploited. \n- Sanitization: No validation or sanitization steps are documented for the input content before it is processed by the agent.

comic-generator