commpeak

Pass

Audited by Gen Agent Trust Hub on May 7, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the @membranehq/cli package via the npm registry. This is a standard vendor-provided tool required for the skill's operation.
  • [COMMAND_EXECUTION]: The skill uses various membrane CLI commands to handle authentication (membrane login), manage connections (membrane connect), and run platform actions. These commands are local executions of the installed vendor tool.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it ingests untrusted data from CommPeak (such as call recordings, search results, or metadata).
  • Ingestion points: External data enters the context via membrane action run and search-results.
  • Boundary markers: None identified in the provided instructions.
  • Capability inventory: The agent can execute shell commands via the CLI and write data to the platform.
  • Sanitization: No explicit sanitization or filtering of remote content is documented within the skill body.
Audit Metadata
Risk Level
SAFE
Analyzed
May 7, 2026, 05:41 AM
Security Audit — agent-trust-hub — commpeak