lov-human-writing

Pass

Audited by Gen Agent Trust Hub on Aug 31, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided Chinese drafts to perform linguistic audits and rewrites, creating a surface for indirect prompt injection where untrusted content could potentially influence agent behavior.
  • Ingestion points: Untrusted content enters the agent's context through file paths passed to the measure.py script via the --input argument (Step 1 in SKILL.md).
  • Boundary markers: The instructions do not define specific delimiters or isolation techniques to separate user-provided drafts from the system's operational instructions.
  • Capability inventory: The skill is granted access to powerful tools including Bash, Write, Edit, Read, Glob, and Grep, and it executes local Python scripts for core functionality.
  • Sanitization: The skill lacks explicit sanitization or filtering mechanisms to identify or neutralize malicious instructions embedded within the processed text files.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 31, 2026, 10:21 PM
Security Audit — agent-trust-hub — lov-human-writing