The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest data from various corporate communication and productivity tools, which serves as a significant attack surface for instructions embedded in external content.
Ingestion points: Instructions in examples/3p-updates.md, examples/company-newsletter.md, and examples/faq-answers.md explicitly direct the agent to gather information from Slack messages, Google Drive documents, emails, and calendar events.
Boundary markers: The prompt templates do not include delimiters or specific instructions for the agent to ignore or isolate instructions found within the ingested data.
Capability inventory: The skill encourages the agent to use high-privilege read tools to access sensitive corporate information across multiple platforms to generate summaries and FAQs.
Sanitization: There are no provided mechanisms or instructions for the agent to sanitize, validate, or escape the content gathered from these external sources before incorporating it into its final output.

internal-comms