The Agent Skills Directory

[SAFE]: No security issues, malicious patterns, or suspicious behaviors were identified in the skill's instructions or metadata.
[PROMPT_INJECTION]: The skill implements an interactive questioning flow that processes user input, which inherently creates a surface for indirect prompt injection. However, this is expected behavior for its stated purpose and no exploitation logic was found. * Ingestion points: User responses to questions presented via the question tool or chat interface. * Boundary markers: Not explicitly defined in this wrapper file; reliance is placed on the delegated grill-with-docs skill. * Capability inventory: The skill utilizes the question tool for user interaction; it does not define any capabilities for network access, file system modification, or arbitrary command execution. * Sanitization: No explicit input validation or sanitization routines are implemented in this UI-focused wrapper.

grill-docs-open