connection-discovery
Pass
Audited by Gen Agent Trust Hub on May 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: No security issues were detected. The skill is composed of natural language instructions for the agent to follow and does not include any scripts, external URL references, or requests for privileged system access.
- [PROMPT_INJECTION]: The skill provides a surface for indirect prompt injection as it instructs the agent to analyze user-provided note content. This is assessed as safe because the skill does not define or request any dangerous tools or capabilities that could be abused via malicious instructions in a note.
- Ingestion points: Target note (SKILL.md)
- Boundary markers: Absent
- Capability inventory: No specific tool usage or system commands are defined within the skill instructions.
- Sanitization: Absent; the skill does not specify any sanitization for external content.
Audit Metadata