contacts-management
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill handles untrusted data such as contact names, email identifiers, and metadata, which represents a potential surface for indirect prompt injection.
- Ingestion points: Untrusted data enters the context via parameters in contact creation (
zavu.contacts.create), updates (zavu.contacts.update), and search filters (zavu.contacts.list). - Boundary markers: The instructions do not specify the use of delimiters or explicit commands to ignore instructions embedded within the processed data.
- Capability inventory: The skill facilitates API-based contact management, including merging contacts and performing network-based introspection of phone numbers and emails.
- Sanitization: There is no mention of input sanitization or validation of data fields for malicious instructions.
Audit Metadata