paid-ads-tiktok
Pass
Audited by Gen Agent Trust Hub on Aug 15, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external data, including TikTok performance exports and product information. This creates an attack surface where instructions embedded in the external data could attempt to influence the agent's behavior.
- Ingestion points: User-supplied goals, product details, creator assets, and TikTok performance exports (SKILL.md).
- Boundary markers: Absent; the instructions do not provide explicit delimiters or warnings to ignore instructions contained within the external data.
- Capability inventory: The agent is instructed to read local files and resolve relative paths, but no specialized tools or network access are granted in this configuration.
- Sanitization: None identified; input data is processed without escaping or validation filters.
- [SAFE]: The skill primarily serves as a navigational pointer to a canonical workflow file. It contains no obfuscated code, hardcoded credentials, or remote code execution patterns.
Audit Metadata