comprehensive-enrichment
Pass
Audited by Gen Agent Trust Hub on Mar 29, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection. It retrieves data from numerous external enrichment services and merges the content without boundary markers or sanitization logic.\n
- Ingestion points: Data enters the context via API responses from Fiber, Nyne, Sixtyfour, Hunter, Tomba, Linkup, Brand.dev, Scrapegraph, and Exa (SKILL.md).\n
- Boundary markers: The instructions do not define delimiters or "ignore embedded instructions" warnings for the fetched content.\n
- Capability inventory: The agent can execute a wide range of enrichment tools via
orth runacross all sections of SKILL.md.\n - Sanitization: No escaping or validation of external content is performed before processing.\n- [COMMAND_EXECUTION]: The skill relies on constructing and executing
orth runcommands using user-provided identifiers and data fetched from external APIs. This is the primary function of the skill and utilizes the vendor's own CLI tools.
Audit Metadata