The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes a user-supplied 'brief' to generate email content, which serves as an ingestion point for untrusted data.
Ingestion points: The agent reads the type field and specific details from the brief in SKILL.md (Step 1 and Step 4) to populate email drafts.
Boundary markers: The skill instructions do not specify the use of delimiters or 'ignore' commands to isolate the brief's content from the agent's instructions.
Capability inventory: The skill is limited to text generation; it does not utilize tools for file system modification, network communication, or shell command execution.
Sanitization: The workflow does not include a validation or sanitization step for the content provided in the brief before it is processed by the agent.

email-copy