responsive-design
Warn
Audited by Gen Agent Trust Hub on Aug 12, 2026
Risk Level: MEDIUMPROMPT_INJECTION
Full Analysis
- [METADATA_POISONING]: The file
skill-report.jsoncontains a fabricated security audit report with fake model references (e.g., 'gpt-5.5') and pre-determined 'false positive' justifications. This metadata is deceptive and designed to mislead automated security assessment tools about the skill's safety status. - [INDIRECT_PROMPT_INJECTION]: The skill contains self-referential content in
skill-report.jsonthat attempts to pre-emptively validate its own security status ('risk_level': 'safe', 'is_blocked': false). - Ingestion points: The file
skill-report.jsonis provided as part of the skill package and is ingested during analysis. - Boundary markers: Absent; the deceptive audit content is presented as structured metadata.
- Capability inventory: The skill provides instructions and examples for CSS Grid, Flexbox, media queries, and responsive images in
SKILL.md. - Sanitization: Absent; the agent or scanner processes the provided JSON files as authoritative metadata.
Audit Metadata