thebig-gavin-marketing-dashboard
Warn
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The installation process involves cloning a repository from an unverified GitHub account (
theBigGavin/marketingdashboard). - [REMOTE_CODE_EXECUTION]: The skill instructs the agent or user to execute commands (
npm install,npm run dev, andnpm start) on the code downloaded from the external repository, which allows for the execution of arbitrary scripts defined in the package's lifecycle. - [INDIRECT_PROMPT_INJECTION]: The dashboard aggregates financial news and AI model usage trends from external sources, creating a surface where malicious instructions could be embedded in the data stream.
- Ingestion points: External data enters the system through endpoints such as
/api/news,/api/openrouter-usage, and/api/mystery-select. - Boundary markers: The instructions do not define delimiters or specific warnings to ignore instructions embedded within the news text or API responses.
- Capability inventory: The skill possesses capabilities for network requests (proxying), file system access (via
.envconfiguration), and executing subprocesses for the dashboard service. - Sanitization: There is no mention of sanitization or filtering protocols for the ingested global financial news or token usage data.
Audit Metadata