The Agent Skills Directory

[SAFE]: The skill integrates with Composio and Rube, which are well-known services for AI agent toolkits. References to these domains are documented neutrally as intended functionality for the skill's purpose.
[PROMPT_INJECTION]: The skill facilitates the ingestion of external data from Confluence pages (e.g., via CONFLUENCE_GET_PAGE_BY_ID and CONFLUENCE_CQL_SEARCH), creating a surface for indirect prompt injection if the source content contains adversarial instructions.
Ingestion points: Data enters the agent context through page retrieval and search tools specified in SKILL.md.
Boundary markers: The instructions do not provide explicit delimiters or guidance to the agent to ignore instructions embedded within the Confluence content.
Capability inventory: The agent possesses write capabilities, including page creation, updates, and deletions.
Sanitization: There are no documented mechanisms for sanitizing or validating the content retrieved from external pages before processing.

confluence-automation