copywriting-skill

Warn

Audited by Gen Agent Trust Hub on Oct 30, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill functions as a pointer/stub that downloads the full implementation and resources from a remote GitHub repository (github.com/judicael-s/Copywriting-skill) using the npx skills add command. This repository is outside the author's primary namespace and is not from a verified trusted organization.
  • [COMMAND_EXECUTION]: The instructions include shell command sequences for the agent to check for the existence of files and verify installation status (e.g., [ -f "$f" ] && ! grep -q "^das:" "$f"). These commands are intended to be run in the local environment to manage the skill's lifecycle.
  • [INDIRECT_PROMPT_INJECTION]: As a tool designed to process and transform text (copywriting), the skill has an attack surface for indirect prompt injection.
  • Ingestion points: Processes user-supplied product descriptions and web content in SKILL.md triggers.
  • Boundary markers: The skill does not define specific delimiters or instructions for the agent to ignore instructions embedded within the text to be rewritten.
  • Capability inventory: Includes file system checks and npx command execution.
  • Sanitization: No sanitization or validation of the input text is specified.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Oct 30, 2026, 07:19 AM