finding-mentors-sponsors
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWNO_CODE
Full Analysis
- [NO_CODE] (SAFE): No Python, JavaScript, or shell scripts are present in the skill package.
- [Data Exposure & Exfiltration] (SAFE): No hardcoded credentials or access to sensitive system paths were detected. The skill explicitly instructs users to maintain confidentiality and use placeholders for sensitive information.
- [Indirect Prompt Injection] (INFO): The skill ingests user career goals and network information. While this creates an ingestion surface for untrusted data, the skill lacks the side-effect capabilities (such as file writing, network requests, or arbitrary command execution) necessary to escalate an injection into a threat.
- [Prompt Injection] (SAFE): Analysis of the instructions revealed no attempts to override AI safety filters or hijack the agent's system prompt.
Audit Metadata