The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of data from untrusted external sources to generate reports and newsletters.
Ingestion points: The files examples/3p-updates.md, examples/company-newsletter.md, and examples/faq-answers.md instruct the agent to gather context from Slack channels, email threads, Google Drive documents, and Calendar events.
Boundary markers: The instructions do not define clear delimiters or "ignore instructions" warnings for the content being processed from external tools.
Capability inventory: The skill leverages the agent's ability to read organizational communication and storage platforms.
Sanitization: There are no instructions for sanitizing, validating, or filtering the content pulled from these external sources, creating a risk that malicious instructions embedded in a Slack message or email could be interpreted as instructions by the agent or propagated into the final communication.

internal-comms