monid
Pass
Audited by Gen Agent Trust Hub on Nov 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to install the global Node.js package
@monid-ai/cli@latestfrom the official NPM registry. This package is the command-line interface for the Monid service. - [COMMAND_EXECUTION]: The skill relies heavily on shell command execution to perform its functions, including CLI setup (
monid setup), API key management (monid keys add), and executing data retrieval tasks (monid run,monid discover). It also usescurlto upload and download files to/from the vendor's storage service (sfs.monid.ai). - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process unstructured data from the open web, social media platforms, and various external APIs, which represents a surface for indirect prompt injection.
- Ingestion points: Data retrieved from external providers (such as Apify, Twitter, or LinkedIn scrapers) via the
monid runcommand is read into the agent's context for analysis or comparison. - Boundary markers: There are no specific instructions or delimiters provided to isolate the potentially untrusted data from the agent's core instructions.
- Capability inventory: The skill has access to shell execution (
monid,npm,curl) and the ability to write files to the local file system using the-oflag. - Sanitization: The instructions do not mention any sanitization or validation of the retrieved content before the agent processes it.
Audit Metadata