explain-like-senior

Pass

Audited by Gen Agent Trust Hub on Feb 21, 2026

Risk Level: SAFE
Full Analysis
  • Prompt Injection (SAFE): The instructions focus on behavioral guidance and optimization strategies without attempting to bypass safety filters or override system prompts.
  • Data Exposure (SAFE): While the skill mentions reading from a local cache directory (.claude/cache/), it does not access sensitive user credentials or exfiltrate data to external domains.
  • Remote Code Execution (SAFE): The provided shell blocks are illustrative examples of internal tool usage (Grep, Read, Glob) for analysis, not commands to download or run external scripts.
  • Indirect Prompt Injection (LOW): As a code explanation tool, it processes untrusted source code. While this is an attack surface, the tool usage described is restricted to read-only analysis tools. Ingestion points: reads source files via Read/Grep tools. Boundary markers: none specified in skill. Capability inventory: Grep, Read, Glob, and cache-writing. Sanitization: not specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 21, 2026, 12:23 PM