skills/new-career-begin/queryweaver/frontend-mobile-development-component-scaffold/Gen Agent Trust Hub
frontend-mobile-development-component-scaffold
Fail
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: CRITICALINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided requirements through the
$ARGUMENTSvariable and interpolates them directly into code templates (e.g., component names, prop names, and descriptions) without explicit sanitization or boundary markers. - Ingestion points: User requirements are ingested via the
$ARGUMENTSplaceholder inSKILL.mdand processed by theComponentAnalyzerlogic. - Boundary markers: The instructions lack explicit boundary markers or directives to ignore embedded instructions within user-provided requirements.
- Capability inventory: The skill generates file content for components, tests, and stories, which are intended to be written to the local file system by the agent.
- Sanitization: There is no logic instructing the agent to sanitize or validate input strings before including them in the generated TypeScript/JavaScript code, which could lead to code injection in the resulting scaffolded files if a user provides malicious input.
Recommendations
- CRITICAL: 1 file(s) identified as malware by FileRep - DO NOT USE
Audit Metadata