The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to process and classify external, untrusted data including creator community comments, DMs, and fan feedback.
Ingestion points: The skill instructions in SKILL.md explicitly list creator community comments, DMs, replies, member posts, and fan feedback as data sources for triage.
Boundary markers: The instructions do not define specific delimiters or boundary markers to isolate the untrusted message text from the agent's core instructions.
Capability inventory: The skill allows for drafting replies and classification. However, SKILL.md includes a strong safety rule that keeps all community and support systems read-only unless the user approves a specific action.
Sanitization: There are no instructions for sanitizing or escaping the content retrieved from community platforms before it is processed by the agent.

community-triage