front-review

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from user files, presenting a vulnerability to indirect prompt injection. \n
  • Ingestion points: The skill reads target files (such as .js, .ts, .vue) via the Read tool as defined in Step 4 of SKILL.md.\n
  • Boundary markers: No delimiters or explicit instructions to disregard embedded commands are provided in the skill instructions.\n
  • Capability inventory: The skill is restricted to Read and Glob tools; it does not have write access or direct network capabilities.\n
  • Sanitization: No sanitization or validation of ingested file content is performed before processing.\n- [EXTERNAL_DOWNLOADS]: The skill optionally fetches framework documentation from the Upstash GitHub repository via the context7 MCP, which is a legitimate and trusted source for up-to-date coding standards.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 07:22 PM
Security Audit — agent-trust-hub — front-review