The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill instructions direct the agent to ingest and summarize data from sources that can be controlled by third parties (e.g., Slack messages, company documents).
Ingestion points: Files examples/3p-updates.md, examples/company-newsletter.md, and examples/faq-answers.md instruct the agent to use Slack, Google Drive, Email, and Calendar to gather updates and answer questions.
Boundary markers: The instructions do not define delimiters or clear boundaries to separate gathered data from the agent's instructions, nor do they include warnings to ignore instructions embedded within the data.
Capability inventory: The skill uses retrieved information to generate text reports, newsletters, and FAQ answers for internal distribution.
Sanitization: There are no instructions provided to sanitize, escape, or validate the content retrieved from external sources before it is incorporated into the final output.

internal-comms