skills/joelhooks/joelclaw/copywriting/Gen Agent Trust Hub

copywriting

Pass

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: LOWPROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection (INFO): The skill ingests untrusted data from .claude/product-marketing-context.md to inform its writing. This creates a surface where an attacker controlling that file could influence agent behavior. However, the risk is mitigated by the skill's lack of execution or network capabilities. 1. Ingestion points: .claude/product-marketing-context.md referenced in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: Limited to markdown text generation and display; no subprocess, network, or file-write tools detected. 4. Sanitization: Absent.
  • Prompt Injection (SAFE): No evidence of instructions designed to bypass agent constraints or reveal system prompts.
  • Data Exposure & Exfiltration (SAFE): No hardcoded credentials or access to sensitive local paths like SSH keys were found.
  • Unverifiable Dependencies & Remote Code Execution (SAFE): The skill does not perform remote downloads, package installations, or dynamic code execution.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 16, 2026, 05:39 PM