The Agent Skills Directory

[SAFE]: The skill content is purely instructional, focusing on marketing strategy, deal negotiation, and compliance without any executable code or dangerous commands.
[INDIRECT_PROMPT_INJECTION]: The skill identifies a potential attack surface by suggesting the agent analyze influencer audience comments and creator content using tools like social-fetch to vet partners.
Ingestion points: External audience comments and creator posts mentioned in the 'Vetting checklist' in SKILL.md.
Boundary markers: The instructions do not define specific delimiters or warnings to ignore malicious instructions within these external data sources.
Capability inventory: The skill references the use of social-fetch and watch-video tools for content analysis.
Sanitization: No procedures are described for sanitizing or filtering instructions from retrieved social media content before processing.

influencer-marketing