venly
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill installs the @membranehq/cli package from the official npm registry. This is a vendor-owned resource used for the skill's primary functionality.\n- [COMMAND_EXECUTION]: The skill instructions utilize various shell commands through the Membrane CLI (e.g., membrane login, connection ensure, action run) to interact with the Venly service.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes data from the external Venly API, which constitutes an attack surface for indirect prompt injection.\n
- Ingestion points: Untrusted data enters the agent context through the outputs of
membrane action runandmembrane requestas specified inSKILL.md.\n - Boundary markers: Absent; the instructions do not implement delimiters or provide warnings to the agent to ignore instructions embedded in the API responses.\n
- Capability inventory: The skill leverages CLI tools to perform network requests and execute blockchain actions, which are powerful capabilities if manipulated.\n
- Sanitization: Absent; the skill does not describe any sanitization, filtering, or validation of the retrieved API data before it is presented to the agent.
Audit Metadata