enrich-contact
Pass
Audited by Gen Agent Trust Hub on Oct 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from the external Lusha database and user-provided arguments, creating a potential surface for indirect prompt injection.
- Ingestion points: Data enters the agent context via the
$ARGUMENTSvariable and the results returned by thecontacts_searchtool. - Boundary markers: The instructions do not define explicit delimiters (like XML tags or clear separators) to isolate external data from the agent's logic.
- Capability inventory: The skill is capable of performing contact lookups via the Lusha toolset.
- Sanitization: The skill mitigates risks by requiring privacy-centric output formatting, such as using initials for names, domain-only email displays, and masking digits in phone numbers, which helps prevent the direct reflection of potentially malicious strings in the final output.
Audit Metadata