onboarding
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external web sources, which serves as a potential vector for indirect prompt injection.
- Ingestion points: Input parameters such as customer name and country are used to trigger web searches across Google News, Reuters, LinkedIn, and various corporate registries as defined in SKILL.md.
- Boundary markers: The skill does not define explicit delimiters or instructions for the agent to distinguish untrusted web content from its own internal logic or prompts.
- Capability inventory: The agent has permissions to create directory structures and generate document files using external libraries such as openpyxl and fpdf2.
- Sanitization: The instructions lack specific validation, filtering, or sanitization protocols for the data retrieved from external sources before it is used to populate templates or influence risk assessment decisions.
Audit Metadata