The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read and summarize information from potentially untrusted external sources, which is a classic indirect prompt injection vector.
Ingestion points: The instructions in examples/3p-updates.md, examples/company-newsletter.md, and examples/faq-answers.md explicitly direct the agent to gather information from Slack posts, Google Drive documents, Emails, and Calendar events.
Boundary markers: The skill lacks explicit instructions for the agent to treat this ingested content strictly as data or to use delimiters that would prevent the LLM from accidentally following instructions embedded within those sources.
Capability inventory: While specific tool manifests are not included, the skill is designed to leverage tools with read access to corporate messaging and document storage services.
Sanitization: There are no provisions for sanitizing or filtering the content retrieved from these external platforms before it is processed by the agent.

internal-comms