strongdm

Pass

Audited by Gen Agent Trust Hub on Apr 22, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Installs the official Membrane CLI (@membranehq/cli) from the NPM registry to facilitate integration. This is a vendor-owned package and is a standard dependency for this skill.
  • [COMMAND_EXECUTION]: Uses the membrane CLI to perform administrative tasks including searching for connectors, managing connections, and executing actions against the StrongDM API.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface due to its handling of untrusted external data.
  • Ingestion points: StrongDM resource metadata, account details, and audit logs retrieved via membrane CLI commands in SKILL.md.
  • Boundary markers: No delimiters or explicit instructions are provided to the agent to ignore embedded commands within the retrieved data.
  • Capability inventory: The skill can execute powerful actions and proxy arbitrary API requests that could modify infrastructure state.
  • Sanitization: There is no evidence of sanitization or validation of the data retrieved from the external API before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 22, 2026, 06:41 PM