The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest data from external platforms, creating a vulnerability surface for indirect prompt injection attacks. 1. Ingestion points: Guidelines in 'examples/3p-updates.md', 'examples/company-newsletter.md', and 'examples/faq-answers.md' instruct the agent to gather context from high-traffic Slack channels, Google Drive documents, and company-wide emails. 2. Capability inventory: The agent accesses and summarizes potentially sensitive internal information using its integrated tools. 3. Boundary markers: The instructions provide no delimiters or 'ignore instructions' warnings to prevent the agent from following malicious commands that might be embedded in the source documents or messages. 4. Sanitization: The skill does not define any steps to validate or sanitize the ingested data before it is processed and reformatted into communication updates.

internal-comms