The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest data from multiple external and internal sources which could contain malicious instructions designed to influence the agent's behavior.
Ingestion points: Instructions in examples/3p-updates.md, examples/company-newsletter.md, and examples/faq-answers.md direct the agent to read content from Slack, Google Drive, Email, Calendar, and External Press.
Boundary markers: No specific boundary markers or instructions to ignore embedded prompts are provided to the agent to distinguish between data and instructions.
Capability inventory: The skill uses tools to read internal communications and documents but does not appear to have file-write or external network-send capabilities outside of its primary reporting function.
Sanitization: There is no mention of sanitizing or validating the content retrieved from these sources before it is processed by the LLM.

internal-comms