The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill identifies a data ingestion surface by processing user-supplied content such as presentations and articles. However, it incorporates a safety measure in its procedure by instructing the agent to restate 'no-touch boundaries' before taking action. Furthermore, the skill lacks any high-risk capabilities such as file system access, network operations, or code execution.
[SAFE]: The skill does not request any additional permissions or tools in its frontmatter. No evidence of obfuscation, hardcoded credentials, or persistence mechanisms was found. The instructions are transparent and aligned with the stated purpose of improving content structure.

enthrall