paid-ads-tiktok
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data from TikTok Ads and creative briefs, establishing a surface for indirect prompt injection attacks. Findings are summarized below:
- Ingestion points: The skill ingests untrusted data from connected TikTok Ads accounts and creator briefs (as described in SKILL.md).
- Boundary markers: There are no explicit delimiters or instructions defined in the skill to isolate ingested external data from the agent's core instructions.
- Capability inventory: The skill possesses write capabilities for TikTok Ads accounts, including "campaign setup" and "approved TikTok Ads changes", which could be abused if the agent is compromised by malicious data.
- Sanitization: No mechanisms for filtering, sanitizing, or validating external content are specified in the provided instructions.
Audit Metadata