lead-enrichment
Pass
Audited by Gen Agent Trust Hub on Mar 29, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the orth CLI tool to execute API requests to external enrichment services. These operations are within the scope of the skill's intended lead-enrichment functionality.
- [DATA_EXPOSURE]: The skill processes and transmits personally identifiable information (PII), such as names and emails, to third-party APIs. This data handling is the primary purpose of the skill.
- [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection by interpolating untrusted lead data into shell commands and API request bodies. 1. Ingestion points: Data is ingested via environment variables and JSON bodies in SKILL.md (e.g., NAME, COMPANY). 2. Boundary markers: None are specified in the provided command examples to separate data from instructions. 3. Capability inventory: The skill performs network requests and data processing via the orth CLI. 4. Sanitization: There is no evidence of input validation or escaping for user-provided data within the instructions.
Audit Metadata