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.py to 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, and Business goals in SKILL.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
Risk Level
SAFE
Analyzed
May 20, 2026, 12:41 AM
Security Audit — agent-trust-hub — budget-optimizer