story-outline-evaluator

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists of natural language instructions for evaluating creative writing. It does not include any executable code, shell scripts, or requests for sensitive permissions.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input in the form of story outlines.
  • Ingestion points: SKILL.md (via user-supplied story outlines and genres).
  • Boundary markers: Absent in the output template, though instructions require adherence to the input content.
  • Capability inventory: None (no file-write, command execution, or network capabilities are present in the skill's instructions or allowed-tools).
  • Sanitization: Absent.
  • Since the skill has no dangerous tools to exploit, this attack surface is considered safe.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 06:49 PM
Security Audit — agent-trust-hub — story-outline-evaluator