build-gpui-apps
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to analyze and modify existing projects, which creates a surface for indirect prompt injection from untrusted source files.
- Ingestion points: The skill uses
scripts/inspect_gpui_project.shto perform a read-only inventory of a project's state, manifests, and lockfiles (SKILL.md). - Boundary markers: There are no explicit instructions for the agent to treat data from the analyzed project as untrusted or to ignore instructions embedded in user-controlled files.
- Capability inventory: The skill has extensive capabilities to execute shell commands, including
cargo run,cargo test, and specific validation scripts (scripts/validate_reference_app.sh), which could be leveraged if malicious instructions were successfully injected through a project file. - Sanitization: No methods for sanitizing or filtering content from target project files before processing are mentioned in the provided instructions.
Audit Metadata