monid
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions to run shell commands for CLI installation and configuration, including
npm install -g @monid-ai/cliandmonid setup. It also includes steps to upload files usingcurlto URLs generated by the vendor's platform. The use of shell-level calculations like$(wc -c < ./photo.png)is also suggested for input parameters.\n- [EXTERNAL_DOWNLOADS]: The skill fetches the Monid CLI and plugin updates from official vendor-owned repositories and domains. These are identified as functional downloads required for the skill's operation.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from web scraping and external APIs, creating a vulnerability surface for indirect prompt injection.\n - Ingestion points: Results from
monid_runandmonid runcommands that retrieve content from the web, social media, and other external sources (SKILL.md).\n - Boundary markers: Absent. No specific delimiters or instructions to isolate or treat scraped data as untrusted are included in the prompt logic.\n
- Capability inventory: Local shell access for CLI commands, file system writes for saving results (
-o results.json), and network interaction via the Monid platform (SKILL.md).\n - Sanitization: Absent. The instructions do not define methods for validating or escaping content retrieved from external sources before it is processed by the agent.
Audit Metadata