carousel-writer

Pass

Audited by Gen Agent Trust Hub on Mar 21, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is restricted to generating text content for social media slides and does not contain any executable code, system commands, or network communication logic.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it reads from .agents/social-media-context.md to establish writing style. 1. Ingestion point: .agents/social-media-context.md (referenced in SKILL.md). 2. Boundary markers: Absent. 3. Capability inventory: Pure text generation (no subprocesses, exec/eval, file-write, or network operations identified). 4. Sanitization: Absent. The risk is considered negligible as the impact is confined to the style of the generated text.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 21, 2026, 12:35 AM