nodejs-expert

Pass

Audited by Gen Agent Trust Hub on Apr 22, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill's instructions and scripts are focused on legitimate development guidance and do not contain malicious patterns or obfuscated code.
  • [COMMAND_EXECUTION]: The 'Memory Protocol' section in SKILL.md directs the agent to execute cat .claude/context/memory/learnings.md. This is a benign operation used to maintain context/memory across sessions in supported agentic environments and does not target sensitive user credentials or system files.
  • [PROMPT_INJECTION]: The skill is designed to ingest and review untrusted code, creating a surface for indirect prompt injection.
  • Ingestion points: Code review and refactoring capabilities specified in the identity and capabilities sections of SKILL.md.
  • Boundary markers: Absent; the skill does not include specific delimiters or instructions to ignore embedded directives in the code being reviewed.
  • Capability inventory: The skill utilizes Bash, Write, Edit, Grep, Glob, and Read tools as defined in the YAML frontmatter.
  • Sanitization: No explicit sanitization or validation of the ingested code content is performed within the skill's logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 22, 2026, 12:21 PM