The Agent Skills Directory

[SAFE]: The skill is entirely instructional and does not contain any malicious code, obfuscation, or instructions to bypass safety guidelines. It facilitates legitimate automation via the Composio platform.
[PROMPT_INJECTION]: The skill defines a workflow for processing external data from Emailable, which represents a potential surface for indirect prompt injection. This is inherent to the skill's purpose as an automation tool.
Ingestion points: Data returned from Emailable API calls (e.g., verification results) via tool outputs.
Boundary markers: The instructions do not specify any delimiters or warnings to ignore embedded instructions in the retrieved data.
Capability inventory: The skill utilizes tools for discovering, connecting, and executing remote tasks, including RUBE_MULTI_EXECUTE_TOOL and RUBE_REMOTE_WORKBENCH.
Sanitization: No sanitization or validation steps are outlined for the data ingested from external sources.

emailable-automation