ads-create
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted external data such as brand profiles, campaign briefs, and audit findings.
- Ingestion points: Untrusted data enters the context via the brand profile, objective, and optional audit findings loaded in Step 1.
- Boundary markers: The instructions lack explicit delimiters or instructions to ignore embedded commands within the processed data.
- Capability inventory: The skill has the capability to write versioned creative briefs and copy decks to the local run directory (Step 7).
- Sanitization: There is no mention of sanitizing, escaping, or validating the external content before it is interpolated into the generation process.
Audit Metadata