ads-creative
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE] (SAFE): The skill contains only markdown instructions and logic for auditing ad creative quality. It does not include any scripts (Python, JS, Bash) or executable logic.
- [DATA_EXPOSURE] (SAFE): The skill references local files such as
ads/references/platform-specs.mdandbenchmarks.md. These are internal reference documents for the audit process and do not involve sensitive system files or credentials. - [REMOTE_CODE_EXECUTION] (SAFE): No remote downloads, package installations, or dynamic execution patterns were detected.
- [PROMPT_INJECTION] (SAFE): The instructions are task-oriented and do not contain attempts to override system prompts or bypass safety filters.
- [INDIRECT_PROMPT_INJECTION] (LOW): While the skill is designed to process external 'creative assets or performance data', it lacks the capabilities (like network access or shell execution) to turn malicious data into a high-risk exploit. Standard boundary markers for external data are recommended during implementation.
Audit Metadata