ad-creative
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEPROMPT_INJECTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill explicitly instructs the AI to suppress standard system behaviors with the directive: "No warnings, notes, or disclaimers. Stick to requested output."\n- [INDIRECT_PROMPT_INJECTION]: The skill processes external user-supplied data (product details, audience data, and proof points) to generate copy, creating a potential vector for indirect injection attacks.\n
- Ingestion points: User-provided data inputs defined in the "Getting Started" section of SKILL.md.\n
- Boundary markers: Absent; there are no delimiters or instructions provided to the agent to treat user data as non-executable or isolated from the main logic.\n
- Capability inventory: The skill primarily focuses on text generation and does not currently specify tool access in the frontmatter.\n
- Sanitization: Absent; the instructions do not include any steps to sanitize, escape, or validate the content of the user-provided inputs.
Audit Metadata