skills/tdimino/claude-code-minoan/sms/Gen Agent Trust Hub

sms

Pass

Audited by Gen Agent Trust Hub on Nov 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONCREDENTIALS_UNSAFEDYNAMIC_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: Untrusted SMS message content is ingested from inbox.jsonl (populated by sms_listen.py) and interpolated into prompts for the claude CLI in sms_respond.py. An attacker could send crafted SMS messages to influence the agent's persona (soul state) or poison user profiles stored in sms_memory.db. While sms_respond.py uses backtick delimiters and explicit instructions to the LLM to ignore markup in the message, the attack surface for indirect injection is present.\n- [COMMAND_EXECUTION]: The skill frequently executes shell commands via subprocess.run. sms_respond.py calls the claude CLI to generate auto-replies, and sms_process_reply.py spawns sms_send.py as a subprocess. These are intended behaviors but represent high-privilege operations within the skill's scope.\n- [CREDENTIALS_UNSAFE]: The shared utility script _sms_utils.py reads sensitive credentials from ~/.claude.json and ~/.config/env/secrets.env. This allows the skill to automatically retrieve API keys for Twilio and Telnyx. Accessing these files is a form of local credential harvesting required for operation.\n- [DYNAMIC_EXECUTION]: The listener and responder daemons (sms_listen.py and sms_respond.py) use os.fork() and related syscalls to run as background processes, a technique used for persistence and standalone operation on the host system.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 6, 2026, 03:22 AM