The Agent Skills Directory

[SAFE]: The skill defines a set of tools to interact with the Ramp API through a dedicated MCP server. All resources and URLs, such as rube.app and composio.dev, are associated with the vendor, composiohq. No unauthorized data exfiltration, obfuscation, or malicious instructions were identified.
[INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it retrieves external data such as transaction memos and merchant details. However, this risk is minimal as the skill lacks exploitable capabilities like file system access or arbitrary command execution. Ingestion points: Tools such as RAMP_GET_ALL_TRANSACTIONS and RAMP_SEARCH_TRANSACTIONS. Boundary markers: None provided in instructions. Capability inventory: The skill is limited to data retrieval; no shell execution or file writing tools are present. Sanitization: Not specified.

Ramp Automation