usersketch
Pass
Audited by Gen Agent Trust Hub on May 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use the
membraneCLI for authentication, connection management, and executing actions against the UserSketch platform. - [EXTERNAL_DOWNLOADS]: Recommends the global installation of the
@membranehq/cliNode.js package. This is a vendor-owned resource matching the author's namespace. - [PROMPT_INJECTION]: Indirect prompt injection surface identified where the agent processes untrusted data from external tool outputs.
- Ingestion points: Data returned to the agent from
membrane action listandmembrane action runcommands in SKILL.md. - Boundary markers: Absent; there are no instructions to delimit tool output or ignore instructions embedded within the API responses.
- Capability inventory: The agent has the ability to execute shell commands via the CLI (documented in SKILL.md).
- Sanitization: Absent; the skill does not provide methods for validating or sanitizing JSON output before it is processed by the agent's context.
Audit Metadata