story-to-infographic

Pass

Audited by Gen Agent Trust Hub on Jul 25, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill processes narrative documents from the filesystem to extract statistics and assertions. This ingestion point represents a standard surface for indirect prompt injection, where malicious text inside a narrative could attempt to influence the generated infographic brief. However, the skill is governed by a rigorous 4-layer validation framework and strict distillation rules that reduce the impact of untrusted text, and the risk is consistent with the skill's primary purpose.\n- [COMMAND_EXECUTION]: The skill employs the Bash tool for routine directory management and file organization (e.g., creating output directories and moving preview images). These operations are restricted to the agent's local workspace and align with the stated purpose of managing project deliverables.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 25, 2026, 01:51 PM
Security Audit — agent-trust-hub — story-to-infographic