project-invitation

Pass

Audited by Gen Agent Trust Hub on Apr 16, 2026

Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [DATA_EXFILTRATION]: The skill performs network requests to data.spuree.com. Although this is the intended domain for the Spuree service, it is not listed among the predefined trusted organizations or well-known services.\n- [PROMPT_INJECTION]: The skill processes user-controllable data from the Spuree API, which presents an indirect prompt injection surface.\n
  • Ingestion points: The projectName, invitedBy, and invitedEmail fields within the InvitationObject are derived from external API responses and can contain attacker-controlled strings.\n
  • Boundary markers: The instructions do not define delimiters or specific instructions for the agent to isolate or treat these fields as untrusted data.\n
  • Capability inventory: The skill provides the agent with the ability to perform state-changing actions such as accepting, declining, and canceling invitations via POST and DELETE requests.\n
  • Sanitization: No input validation or data sanitization measures are specified for the metadata retrieved from the API.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 16, 2026, 07:00 AM