story-short-analyze

Pass

Audited by Gen Agent Trust Hub on May 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists entirely of markdown instructions and reference templates. It does not utilize external scripts, perform network operations to untrusted domains, or include obfuscated content.
  • [COMMAND_EXECUTION]: The skill instructs the agent to organize output by creating directories and writing reports to a local path (拆文库/{书名}/). This is a standard and safe operation for a writing assistant designed to produce analysis documentation.
  • [PROMPT_INJECTION]: The skill possesses a standard attack surface for indirect prompt injection as it is designed to process and analyze user-provided story content.
  • Ingestion points: User-supplied story text entered during Phase 1 for analysis.
  • Boundary markers: Absent; the instructions do not explicitly warn the agent to ignore or isolate potential instructions embedded within the analyzed story text.
  • Capability inventory: The agent's primary capabilities within this skill are text generation and writing files to the local directory.
  • Sanitization: None; the skill processes the user's story input directly to apply its analytical frameworks.
Audit Metadata
Risk Level
SAFE
Analyzed
May 13, 2026, 06:46 AM