j-idol
Pass
Audited by Gen Agent Trust Hub on Feb 26, 2026
Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
- [SAFE]: Analysis of the skill instructions reveals no malicious patterns, hardcoded credentials, or unauthorized system access attempts.\n- [NO_CODE]: This skill consists entirely of instructional markdown and does not include any scripts, executables, or code files.\n- [PROMPT_INJECTION]: The skill contains a surface for indirect prompt injection because it processes untrusted user-provided reference images.\n
- Ingestion points: Reference images are analyzed in Step 1 to understand character identity.\n
- Boundary markers: Absent; the instructions do not include delimiters or directives to ignore instructions that might be embedded in reference data.\n
- Capability inventory: The skill is restricted to generating image prompts and lacks network, file system, or tool-use capabilities.\n
- Sanitization: Absent; the skill does not specify any validation or sanitization steps for the input reference images.
Audit Metadata