deno-expert
Pass
Audited by Gen Agent Trust Hub on May 3, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill uses strong instructional language and negative constraints (e.g., 'CRITICAL: Never Write Deprecated URLs') to define its persona and ensure responses adhere to modern Deno standards. These instructions are focused on technical quality and legacy code migration rather than overriding safety filters.
- [EXTERNAL_DOWNLOADS]: The skill provides links to official Deno documentation and the JSR registry (docs.deno.com, jsr.io, fresh.deno.dev). These are well-known, trusted domains within the technology ecosystem.
- [COMMAND_EXECUTION]: The skill includes various CLI command examples (e.g.,
deno fmt,deno lint,deno run) as educational references for the user. It does not contain instructions for the agent to execute these commands automatically, silently, or with elevated privileges. - [PROMPT_INJECTION]: The skill acts on user-provided code for review and debugging, creating a surface for indirect prompt injection. There are no explicit instructions for the agent to sanitize or ignore instructions embedded within the code samples it processes, which is a common risk for code analysis tools.
Audit Metadata