thebig-gavin-marketing-dashboard
Pass
Audited by Gen Agent Trust Hub on Aug 1, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructions require cloning a repository from GitHub (github.com/theBigGavin/marketingdashboard.git) and installing dependencies via 'npm install'. This process downloads and executes code from an external repository to build and deploy the dashboard.
- [PROMPT_INJECTION]: The skill aggregates global financial news and processes industry chain text, creating a surface for indirect prompt injection where instructions embedded in external content could influence the agent's behavior.
- Ingestion points: External data enters the context via '/api/news', '/api/quotes', and '/api/stock-search' endpoints.
- Boundary markers: No specific boundary markers or 'ignore embedded instructions' warnings were identified to delimit the processed data.
- Capability inventory: The skill environment requires command execution for setup (npm, docker), although these are not directly integrated into the data processing flow.
- Sanitization: The documentation does not specify any sanitization, filtering, or validation of the ingested news data.
- [COMMAND_EXECUTION]: The installation and deployment workflow involves several shell commands, including 'git clone', 'npm install', 'npm run build', and 'docker run'. These commands are used for the intended purpose of setting up a local or production environment for the dashboard.
Audit Metadata