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