The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill acts on untrusted data from external creator profiles and campaign briefs which could potentially contain adversarial instructions.
Ingestion points: SKILL.md specifies that the agent should process creator profiles and briefs provided by the user.
Boundary markers: There are no defined delimiters or instructions to ignore instructions found within the ingested data.
Capability inventory: The skill leverages Read and Write tools as declared in the SKILL.md configuration.
Sanitization: The skill lacks explicit validation or sanitization mechanisms for the external inputs.

creator-vetting