The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes external customer interview data, which serves as an ingestion point for potentially untrusted content that could influence the agent's behavior.
Ingestion points: Raw interview notes and verbatim customer quotes are ingested into the agent's context as specified in SKILL.md.
Boundary markers: The instructions do not specify the use of delimiters or clear markers to separate untrusted interview content from the agent's primary instructions.
Capability inventory: The skill instructs the agent to update and modify the local .agents/marketing-strategy.md file based on the analysis of these interviews.
Sanitization: There are no instructions provided for sanitizing, validating, or filtering the external text before it is incorporated into the internal strategy documents.

grill-me