review-vue
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external source code (.vue and .ts files) which could contain malicious instructions hidden in comments or strings intended to manipulate the agent's review findings.
- Ingestion Points: The skill ingests data via the
input_schemawhich accepts source files or directories. - Boundary Markers: The instructions do not define specific delimiters or "ignore instructions" directives to isolate the code being analyzed from the agent's core logic.
- Capability Inventory: The skill is atomic and restricted to generating a findings list; it lacks capabilities for network access, file system modifications (writes), or command execution.
- Sanitization: There is no explicit requirement for the agent to sanitize or escape the content of the analyzed files before processing.
Audit Metadata