create-shortform

Pass

Audited by Gen Agent Trust Hub on Aug 21, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists entirely of markdown instructions for content creation, research, and evaluation. No malicious commands, obfuscated content, or unauthorized network operations were identified.- [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for processing external data such as platform trends and product evidence, which is a common requirement for its stated purpose.
  • Ingestion points: External trend evidence and brand/product material mentioned in SKILL.md.
  • Boundary markers: The instructions explicitly define an "evidence boundary" and "external-action boundary" to scope the agent's output.
  • Capability inventory: No high-privilege tools or dangerous system operations are requested or utilized within the provided scripts.
  • Sanitization: The skill emphasizes the use of "real UI" and "dated samples" to ensure data integrity during the research process.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 21, 2026, 11:56 PM
Security Audit — agent-trust-hub — create-shortform