The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from various external and internal sources, creating a surface for indirect prompt injection.
Ingestion points: The agent is instructed to read local context files like .agents/product-marketing.md and fetch external content using tools such as social-fetch to evaluate creator profiles.
Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from following commands that might be embedded within the retrieved social media content or local product descriptions.
Capability inventory: The skill uses tools to fetch external data and has read access to the local project structure.
Sanitization: The skill does not define specific validation or sanitization routines for the data it processes.

influencer-marketing