NYC

frontend-angular-store

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • Prompt Injection (SAFE): The 'MUST READ' and 'IMPORTANT' instructions are natural instructional language for a coding assistant and do not attempt to override system safety guidelines or extract system prompts.\n- Indirect Prompt Injection (SAFE): The skill defines a surface for ingesting data by instructing the agent to read external documentation files.\n
  • Ingestion points: SKILL.md (MUST READ section) points to local markdown files in .claude/skills/ and docs/.\n
  • Boundary markers: Absent, however, these are internal documentation paths.\n
  • Capability inventory: Read, Write, Edit, Grep, Glob, Bash.\n
  • Sanitization: Not applicable as the data is from trusted internal sources.\n- Command Execution (SAFE): The skill requests access to the Bash tool but provides only a benign grep command for searching the source code for existing patterns.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:23 PM