resale-flip-kit
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user data such as item descriptions, brand names, and condition notes to generate listings.
- Ingestion points: Inputs defined in SKILL.md include brand, size, age, condition, flaws, and platform names.
- Boundary markers: The framework does not specify the use of delimiters or 'ignore' instructions to encapsulate user-provided data within the prompt.
- Capability inventory: Analysis of the skill body shows no shell command execution, filesystem writing, or network operations.
- Sanitization: The instructions do not include specific steps to sanitize or validate the external content before processing it.
Audit Metadata