robocorp
Pass
Audited by Gen Agent Trust Hub on Apr 21, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill facilitates the download and installation of the
@membranehq/clipackage from the npm registry. This is a vendor-provided tool required for the skill's functionality. - [COMMAND_EXECUTION]: Executes shell commands using the
membraneCLI to manage connections, search for robots, and run RPA actions. This includes usingnpxto execute the latest version of the tool dynamically. - [PROMPT_INJECTION]: The skill ingests and processes structured data from external Robocorp APIs (via CLI output), creating a surface for potential indirect prompt injection.
- Ingestion points: Outputs from
membrane action list,membrane search, andmembrane action runcommands inSKILL.md. - Boundary markers: No specific delimiters are used to wrap the tool outputs in the provided instructions.
- Capability inventory: The skill has the ability to execute shell commands and perform network operations via the Membrane proxy.
- Sanitization: There are no explicit instructions for sanitizing or validating the content returned by the CLI commands before the agent processes it.
Audit Metadata