article-illustrations
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it processes untrusted user-provided articles.
- Ingestion points: Articles are ingested through Examples 1 and 2 in
SKILL.md. - Boundary markers: Absent; no specific delimiters or ignore-embedded-instruction markers are defined for the input content.
- Capability inventory: Accesses the
image-generationtool. - Sanitization: Absent; input text is not sanitized before being used to generate image prompts.
- [SAFE]: The skill contains no executable scripts or command-line operations.
- [SAFE]: No sensitive file access, network exfiltration, or hardcoded credentials were detected.
- [SAFE]: External references point to a GitHub repository for documentation and licensing, which is consistent with the skill's metadata.
Audit Metadata