Skills
Navigate
skills/wuyoscar/jev-skill/jev-find-code/Gen Agent Trust Hub

jev-find-code

Pass

Audited by Gen Agent Trust Hub on Sep 21, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the jev-skill package, hosted at github.com/wuyoscar/jev-skill.
  • [COMMAND_EXECUTION]: The skill uses the jev-decide CLI tool to perform code location analysis.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes project-specific data (file paths and summaries) which is then transmitted to external AI providers.
  • Ingestion points: assets/example.json and user-provided project files or summaries.
  • Boundary markers: The skill explicitly instructs the agent to wait for an explicit user choice between providers and modes before proceeding.
  • Capability inventory: Network transmission of evidence to OpenRouter and TypeSafe APIs via the jev-decide CLI.
  • Sanitization: Instructions explicitly direct the agent to omit secrets and unrelated files from the evidence sent to external providers.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 21, 2026, 08:44 AM