company-deep-dive
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to research companies by ingesting data from the web, which introduces a potential vector for indirect prompt injection.
- Ingestion points: Data is collected from external sources using nimble search and nimble extract commands as part of the research workflow.
- Boundary markers: The skill structures its findings into reports but does not use specific delimiters to isolate untrusted web content during its processing phases.
- Capability inventory: The agent has permissions for Bash command execution, file system operations (Write, Edit), and spawning sub-agents.
- Sanitization: The skill relies on the LLM's inherent processing capabilities to handle external data without additional programmatic sanitization steps.
- [EXTERNAL_DOWNLOADS]: The skill instructions facilitate the installation and management of the nimble-cli tool from the NPM registry to provide the necessary research capabilities.
Audit Metadata