revor-company-research
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a bundled Node.js script (
scripts/revor-api.mjs) to perform API calls and manage configuration settings. - [INDIRECT_PROMPT_INJECTION]: The skill ingests external data from web searches, trade records, and contact databases which could contain adversarial content.
- Ingestion points: External data enters the agent context through the outputs of the Revor research tools (e.g.,
revor_research_public_web,revor_customs_full_report). - Boundary markers: The instructions guide the agent on how to resolve identity but do not specify clear delimiters or warnings to ignore embedded instructions in the retrieved data.
- Capability inventory: The skill has the capability to execute a local Node.js script, make network requests to the vendor's API, and read local configuration files.
- Sanitization: While the script parses API responses as structured JSON, there is no explicit sanitization of text content before it is processed by the agent.
Audit Metadata