inksprout

Pass

Audited by Gen Agent Trust Hub on Apr 23, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the global npm package @membranehq/cli, which is the official command-line interface provided by the vendor.
  • [COMMAND_EXECUTION]: The skill relies on executing shell commands via the membrane CLI to manage connections, list actions, and perform API requests.
  • [PROMPT_INJECTION]: The skill contains a surface for indirect prompt injection where untrusted external data could influence the agent. * Ingestion points: External content is ingested via the 'summarize-content' action using URLs or raw text inputs. * Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands mentioned in the SKILL.md. * Capability inventory: The skill has the capability to execute shell commands and perform network requests via the membrane CLI. * Sanitization: There is no evidence of sanitization or validation of the external content before it is processed by the AI for summarization.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 23, 2026, 09:08 AM