echtpost-postcards

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Installs the @membranehq/cli package globally via npm to facilitate interaction with the Membrane platform. This is a legitimate vendor-owned resource.\n- [COMMAND_EXECUTION]: Uses the membrane CLI to execute commands for logging in, managing connections, and performing API requests (SKILL.md).\n- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it processes untrusted data from the EchtPost API.\n
  • Ingestion points: Data returned from actions like listing contacts or postcards via membrane action run and membrane request (SKILL.md).\n
  • Boundary markers: The skill does not define specific markers to separate API-provided content from agent instructions.\n
  • Capability inventory: The agent can execute system commands via the membrane CLI.\n
  • Sanitization: There is no evidence of sanitization or filtering of the external API content before it is ingested into the prompt context.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 05:23 PM