bezalel-connectors
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill acts as an interface for hundreds of third-party applications (GitHub, Slack, Gmail, etc.), which creates a significant surface for indirect prompt injection from malicious external data.
- Ingestion points: The
connectors__executetool retrieves potentially untrusted content from these third-party services. - Boundary markers: The instructions lack explicit requirements for the agent to use delimiters or ignore instructions found within the retrieved data.
- Capability inventory: The agent possesses the capability to execute actions and write data to these systems using the
connectors__executetool. - Sanitization: There are no instructions or built-in mechanisms for the agent to sanitize or validate content returned from the external connectors.
Audit Metadata