The Agent Skills Directory

Indirect Prompt Injection Surface: The skill is designed to ingest large amounts of unstructured data from Slack, Google Drive, Email, and Calendars to generate summaries, newsletters, and FAQs. This represents a potential vulnerability surface where malicious instructions embedded in that external data could influence the agent's behavior during the generation process.
Ingestion points: The skill reads from Slack channels, Google Drive documents, emails, and calendar events across multiple guideline files (examples/3p-updates.md, examples/company-newsletter.md, examples/faq-answers.md).
Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' prompts when processing this external data.
Capability inventory: The skill possesses the capability to read extensive organizational data and output formatted text that may be distributed via Slack or email.
Sanitization: There is no evidence of sanitization or filtering logic to detect or ignore prompt injection attempts hidden within the source communications.

internal-comms