copywriting

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [NO_CODE] (SAFE): The skill is composed strictly of markdown files (SKILL.md, ai-tropes.md, frameworks.md) and contains no executable scripts (Python, Node.js, or Shell). This inherently prevents technical attack vectors such as Remote Code Execution or privilege escalation.
  • [SAFE] (SAFE): No malicious instructions, prompt injection attempts, or obfuscation techniques were identified within the skill's content. The instructions are aligned with its stated purpose of professional copywriting.
  • [Indirect Prompt Injection] (SAFE): The skill is designed to ingest and follow instructions from external markdown files located in a local directory (~/Documents/copywriting/copyhackers-prompts/). Although this represents an input surface for instructions, the risk is negligible because the skill does not possess any capabilities for network access, file writing, or command execution. Evidence: 1. Ingestion points: Local files in user's Documents folder. 2. Boundary markers: Absent. 3. Capability inventory: No tools or code provided. 4. Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:48 PM