app-description-writer

Pass

Audited by Gen Agent Trust Hub on Jun 18, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists entirely of natural language instructions, templates, and best practices for copywriting. It does not include any scripts, shell commands, or binary files.
  • [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection as it is designed to process and improve existing user-provided app descriptions. This could allow malicious instructions embedded in a description to influence the agent's behavior.
  • Ingestion points: Processes existing copy or promotional text as mentioned in the skill description and instructions.
  • Boundary markers: Absent; the instructions do not define specific delimiters to separate user data from the system prompt.
  • Capability inventory: Access is limited to standard file operations (Read, Write, Edit, Glob, Grep) and user interaction (AskUserQuestion).
  • Sanitization: Absent; the skill does not instruct the agent to sanitize or validate the content of the descriptions it processes.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 18, 2026, 05:18 PM
Security Audit — agent-trust-hub — app-description-writer