mason

Pass

Audited by Gen Agent Trust Hub on Apr 3, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: Uses the membrane CLI to manage connections and execute actions within the Mason ecosystem.
  • [EXTERNAL_DOWNLOADS]: Downloads and installs the @membranehq/cli package, which is the official tool provided by the vendor for this integration.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it retrieves and processes data from external Mason API endpoints.
  • Ingestion points: Data enters the agent context through membrane action run and membrane request commands described in SKILL.md.
  • Boundary markers: The instructions do not specify the use of delimiters or warnings to ignore potentially malicious instructions within the retrieved data.
  • Capability inventory: The skill allows for command execution and network operations through the membrane CLI as defined in SKILL.md.
  • Sanitization: There is no evidence of sanitization or filtering of the content received from the external API in the provided documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 3, 2026, 06:49 PM