novel-truncator

Pass

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: LOWPROMPT_INJECTIONNO_CODE
Full Analysis
  • NO_CODE (SAFE): The skill consists entirely of markdown instructions and examples. There are no executable scripts, binaries, or tool definitions (allowed-tools is empty), which eliminates risks associated with command execution or remote code.
  • PROMPT_INJECTION (LOW): The skill is susceptible to indirect prompt injection (Category 8) as it processes untrusted novel text. 1. Ingestion points: The 'Text Content' input described in SKILL.md. 2. Boundary markers: Absent; the prompt does not use delimiters or instructions to ignore embedded commands. 3. Capability inventory: None; the skill's allowed-tools list is empty and no scripts are present. 4. Sanitization: Absent; the input is processed as raw text without validation. The impact is limited to output corruption since no high-privilege capabilities are exposed.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 16, 2026, 06:08 AM