brand-dev
Pass
Audited by Gen Agent Trust Hub on Apr 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses shell commands (
curl,grep,mkdir,ls) to retrieve API keys, fetch brand data, and manage local files. These commands incorporate variables like${DOMAIN}and<logo-url>which are derived from user input or external API responses. - [EXTERNAL_DOWNLOADS]: The skill is designed to download image files (logos) from remote URLs provided by the brand.dev API and save them to the local project directory.
- [PROMPT_INJECTION]: The skill is vulnerable to Indirect Prompt Injection (Category 8).
- Ingestion points: Data fields such as
.brand.titleand.brand.descriptionare fetched from the externalapi.brand.devservice. - Boundary markers: None. The fetched data is presented directly to the agent context.
- Capability inventory: The skill has the ability to execute shell commands (
curl,mkdir,ls) and write to the local filesystem. - Sanitization: There is no evidence of sanitization or validation for the brand descriptions or titles before they are processed by the agent.
Audit Metadata