story-type-analyzer

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • SAFE (SAFE): The skill is entirely instructional and documentation-based. It does not include any scripts (Python/JS) or shell commands.
  • [Category 8] Indirect Prompt Injection (SAFE): While the skill is designed to process untrusted user input (story summaries), it poses no significant risk as it lacks dangerous capabilities.
  • Ingestion points: User-provided story text, outlines, or synopses as defined in SKILL.md.
  • Boundary markers: No explicit delimiter or 'ignore' instructions are defined for the input text.
  • Capability inventory: The skill only requests the 'Read' tool, preventing file system modification, network access, or command execution.
  • Sanitization: No sanitization logic is present, but the restricted toolset mitigates the risk of processing malicious instructions embedded in stories.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:33 PM