paid-ads
Pass
Audited by Gen Agent Trust Hub on Apr 29, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill includes a design pattern that ingests data from external context files, creating a surface for indirect prompt injection.
- Ingestion points: The skill reads marketing context from
.agents/product-marketing-context.mdor.claude/product-marketing-context.mdas specified in SKILL.md. - Boundary markers: Absent; there are no instructions to use delimiters or to disregard potentially malicious instructions within the context files.
- Capability inventory: The skill has broad capabilities to manage ad platform accounts, including creating campaigns, setting budgets, and adjusting bidding strategies (SKILL.md).
- Sanitization: Absent; the skill does not perform validation or sanitization of the ingested context file content.
Audit Metadata