The Agent Skills Directory

[SAFE]: The skill operates entirely within its declared scope of verifying content. It does not attempt to access sensitive files, maintain persistence, or execute arbitrary code.
[PROMPT_INJECTION]: The skill is designed to process untrusted user data (messages, images, and text) to verify authenticity, which creates a surface for indirect prompt injection.
Ingestion points: SKILL.md processes user-provided information and content.
Boundary markers: None present. The instructions do not specify delimiters to separate user content from system instructions.
Capability inventory: The skill uses the openclaw tool in SKILL.md to perform network searches and message-based tasks.
Sanitization: No explicit sanitization or validation of user-provided content is mentioned before it is passed to the search tool.

verify-authenticity