eeailab-picturebook

Pass

Audited by Gen Agent Trust Hub on Nov 13, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill contains no executable code, scripts, or system-level commands. It functions strictly through natural language instructions and markdown templates to guide a creative workflow.
  • [SAFE]: Includes explicit privacy protections. The instructions require the agent to warn users about protecting child privacy when using personal photos and advise against uploading sensitive imagery to untrusted platforms.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input (story ideas and themes) to generate structured outputs. However, this is categorized as safe because the skill does not possess any capabilities (such as network access, file system writes, or tool invocation) that could be exploited by an injection attack.
  • [METADATA_POISONING]: The skill includes promotional metadata and a mandatory attribution rule (slogan and contact info). While promotional, these elements do not contain malicious instructions, obfuscated commands, or attempts to bypass AI safety guardrails.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 13, 2026, 02:35 PM