The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill provides instructions for analyzing external data sources which represents a potential attack surface for indirect prompt injection.
Ingestion points: Influencer content, audience comments, and media kits processed during the vetting and sourcing phases (SKILL.md).
Boundary markers: The instructions lack explicit delimitation or warnings to disregard instructions that may be present in the external data being analyzed.
Capability inventory: The skill uses tools like social-fetch and watch-video to retrieve external data for analysis.
Sanitization: No specific methods for sanitizing or validating external inputs are described in the instructions.

influencer-marketing