The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest project-specific documentation, creating a surface for indirect prompt injection where instructions hidden in those files could influence agent behavior.
Ingestion points: The agent is instructed to read context from files named .agents/product-marketing.md, .claude/product-marketing.md, or product-marketing-context.md in the Initial Assessment section of SKILL.md.
Boundary markers: The instructions lack explicit boundary markers or warnings for the agent to ignore embedded instructions within the ingested marketing files.
Capability inventory: The skill does not utilize dangerous capabilities such as network requests, file writes, or arbitrary command execution.
Sanitization: There is no evidence of sanitization or validation logic for the content read from the external marketing context files.

signup