skills/supsub-ai/supsub-cli/supsub-mp/Gen Agent Trust Hub

supsub-mp

Pass

Audited by Gen Agent Trust Hub on Jul 30, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill provides installation instructions that download a shell script from the vendor's official repository (github.com/SupSub-AI/supsub-cli) and pipe it to bash.
  • [EXTERNAL_DOWNLOADS]: The skill references an external installation script and suggests installing the '@supsub/cli' package from the global NPM registry, both of which originate from the skill vendor's official channels.
  • [COMMAND_EXECUTION]: The agent is instructed to execute local CLI commands, including 'supsub mp search' and 'supsub auth login', to interact with the service and manage authentication.
  • [PROMPT_INJECTION]: The skill processes data from external sources (WeChat account descriptions) which are interpolated into the agent's context, creating an indirect injection surface. 1. Ingestion points: WeChat account search results (SKILL.md). 2. Boundary markers: None explicitly defined for search data. 3. Capability inventory: System command execution and follow-up actions like 'supsub sub add'. 4. Sanitization: No automated sanitization is specified; the skill relies on mandatory human confirmation before selection.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 30, 2026, 01:15 AM
Security Audit — agent-trust-hub — supsub-mp