The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core functionality of ingesting and processing data from external sources.
Ingestion points: Content is retrieved from user-linked documents, uploaded files, and messaging/storage connectors such as Slack, Teams, Google Drive, and SharePoint (referenced in SKILL.md).
Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions for data fetched from these external sources.
Capability inventory: The skill uses file system tools like create_file and str_replace to generate documentation and invokes sub-agents for testing purposes.
Sanitization: No sanitization or validation of external content is implemented before it is processed by the agent.

doc-coauthoring