budget-optimizer
Pass
Audited by Gen Agent Trust Hub on May 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: Executes a local Python script located at
scripts/budget-optimizer.pyto process budget data and generate optimization scenarios. - [PROMPT_INJECTION]: The skill ingests untrusted user input including channel performance data, business goals, and historical context.
- Ingestion points: Input parameters such as
Current budget by channel,Performance data by channel, andBusiness goalsinSKILL.md. - Boundary markers: No explicit delimiters (like XML tags) or instructions are provided to the agent to treat this data as untrusted or to ignore embedded instructions.
- Capability inventory: The skill executes a local script (
scripts/budget-optimizer.py) and utilizes specialized agents (analytics-analyst,media-buyer) to process this information. - Sanitization: No evidence of input validation, escaping, or filtering of the user-provided content is present in the instructions.
Audit Metadata