electron-app-audit
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to process and analyze local Electron packages and application paths, creating a surface for indirect prompt injection.
- Ingestion points: Local installers, packages, and application directory paths (SKILL.md).
- Capability inventory: The workflow involves identifying entrypoints, inspecting install chains, and analyzing packaging layouts, which requires broad file system read access and potential use of archive-parsing tools.
- Boundary markers: The instructions do not define delimiters or specific warnings to ignore natural language instructions that might be embedded within the target application's metadata or scripts.
- Sanitization: There are no instructions for sanitizing or escaping content retrieved from the target package before the agent interprets it.
Audit Metadata