The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from Atlassian Confluence, which serves as an external and untrusted data source.
Ingestion points: Untrusted data enters the agent's context through tools such as confluence_read, confluence_search, confluence_comments, and confluence_attachments.
Boundary markers: The skill does not implement technical delimiters or boundary markers to isolate external content; it relies on natural language instructions within the documentation to warn the agent that all text returned from Confluence is untrusted.
Capability inventory: The skill provides extensive capabilities that could be exploited if an injection occurs, including shell access via the Bash tool, file system Write operations, and various Confluence mutation tools like confluence_update and confluence_delete.
Sanitization: There is no mention of automated sanitization, filtering, or validation of the external content before it is processed by the agent.

confluence