run-paid-campaigns-health-gate
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from multiple external sources, creating an attack surface where malicious content embedded in ads or landing pages could attempt to influence the agent's behavior.
- Ingestion points: Destination URLs, marketer exports, performance reports in
reports/performance/, and product records (SKILL.md). - Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat the contents of these external sources as untrusted data or to ignore potential instructions embedded within them.
- Capability inventory: The skill performs file reads (
state.md,reports/performance/), and requires the agent to browse destination URLs and analyze marketer exports. - Sanitization: No sanitization, escaping, or validation logic is defined for the external data ingested during the audit process.
Audit Metadata