ads-create
Pass
Audited by Gen Agent Trust Hub on Aug 20, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes untrusted user data (campaign briefs, concepts) without using boundary markers or sanitization logic.\n
- Ingestion points: The skill triggers on and processes user-provided inputs such as campaign brief, campaign concepts, and ad concepts as defined in SKILL.md.\n
- Boundary markers: The instructions do not define specific delimiters or warnings to ignore embedded instructions within the processed campaign data.\n
- Capability inventory: The skill is restricted to reading local reference files (e.g., ads/references/google-creative-specs.md) and writing output to the run directory; it lacks network access or arbitrary command execution capabilities.\n
- Sanitization: No input validation or escaping mechanisms are described in the instructions.\n- [NO_CODE]: The skill consists entirely of natural language instructions and does not include any executable scripts or configuration files that could perform actions independently of the agent context.
Audit Metadata