instantly-enterprise-rbac
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from the Instantly.ai API (member lists, API key metadata, and audit logs) and has high-privilege capabilities that could be influenced by malicious content in those external sources.
- Ingestion points: Data enters the agent context through API responses from endpoints like
/workspace-members,/api-keys, and/audit-logs(referenced in SKILL.md). - Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are present in the data processing snippets.
- Capability inventory: The skill possesses the ability to perform high-privilege actions via the
client.requestmethod, including inviting or deleting workspace members, creating or revoking API keys, and transferring workspace ownership. - Sanitization: The skill does not implement explicit sanitization of API response data, although it does include a directive in the 'Output' section to use opaque IDs and avoid copying recipient lists in its final report.
Audit Metadata