nanobanana-ppt
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill manifest directs users to an external, untrusted GitHub repository (github.com/op7418/NanoBanana-PPT-Skills) to download and install a bundle containing assets and scripts. This involves integrating unverified third-party code into the agent's environment.
- [INDIRECT_PROMPT_INJECTION]: The skill performs document analysis to generate structured PPT decks, which provides a surface for malicious instructions hidden in input documents to influence the agent.
- Ingestion points: Document analysis feature described in the skill body (SKILL.md).
- Boundary markers: None identified in the provided manifest.
- Capability inventory: Structured deck generation and styled image creation.
- Sanitization: No sanitization or filtering logic is specified for the ingested content.
Audit Metadata