workboard
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided inputs for search intents and action parameters, which represents a potential attack surface for indirect prompt injection. 1. Ingestion points: user-supplied arguments for CLI commands in SKILL.md. 2. Boundary markers: None. 3. Capability inventory: Shell command execution and network proxy access. 4. Sanitization: None.
- [EXTERNAL_DOWNLOADS]: The skill instructions include installing the @membranehq/cli package from the npm registry, which is a vendor-owned tool for this integration.
- [COMMAND_EXECUTION]: Interaction with the Workboard service is performed via shell commands using the Membrane CLI tool.
Audit Metadata