The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from various untrusted external sources, creating a significant surface for indirect prompt injection attacks where malicious instructions hidden in external content could manipulate the agent's behavior.
Ingestion points: Untrusted data is retrieved from Slack messages, Google Drive documents, emails, calendar event details, and external press articles, as specified in examples/3p-updates.md, examples/company-newsletter.md, and examples/faq-answers.md.
Boundary markers: The instructions do not provide any boundary markers, delimiters, or explicit warnings to the agent to ignore or isolate embedded instructions within the source data.
Capability inventory: The skill utilizes the agent's integrated tools for accessing corporate communication platforms and document repositories (Slack, Google Drive, Email, Calendar) to gather context for writing updates and FAQs.
Sanitization: There is no evidence of sanitization, validation, or escaping logic applied to the external content before it is interpolated into the agent's prompt context.

internal-comms