chatgpt-app-submission
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [Indirect Prompt Injection Surface]: The skill analyzes external codebase files, including READMEs and source code, which serves as a potential ingestion point for untrusted data. This creates a surface for indirect prompt injection, though the skill implements mitigations such as concise output constraints and human-in-the-loop approval requirements.
- [Source Code Modification]: The skill is capable of modifying tool hints in the server source code when developer approval is granted. While this is an intended feature to ensure submission compliance, automated modification of project source files is a capability that should be monitored during execution.
- [Sensitive Data Verification]: The skill explicitly checks tool descriptors for the solicitation of highly sensitive information, such as PHI, PCI, or credentials. This proactive auditing helps developers identify and mitigate potential privacy risks before submission.
Audit Metadata