ad-budget-pacing
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is composed of instructional markdown and reference notes for budget pacing. It does not contain executable code, remote script executions, or requests for sensitive system permissions. The references to external domains and internal skill repositories within the mbfinotti namespace are used for documentation and modular functionality. No evidence of prompt injection, obfuscation, or persistence mechanisms was found.
- [INDIRECT_PROMPT_INJECTION]: The skill identifies a potential surface for indirect prompt injection as it involves processing performance data and status messages from external advertising platforms. 1. Ingestion points: The skill is intended to process ad campaign metrics (spend, budget, dates) and platform-generated status messages (e.g., Google Ads 'Limited by budget' status). 2. Capability inventory: No tools or functions providing shell access, network operations, or file system writes are defined in the skill. 3. Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions when handling untrusted ad data. 4. Sanitization: No input validation or sanitization logic is described for the data processed by the analyst persona.
Audit Metadata