skills/iflytek/skillhub/zero-slop/Gen Agent Trust Hub

zero-slop

Pass

Audited by Gen Agent Trust Hub on Nov 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a bundled Python script (scripts/slopscore.py) to perform prose scoring and factual fidelity checks.
  • [INDIRECT_PROMPT_INJECTION]:
  • Ingestion points: The skill processes user-supplied text drafts (untrusted data).
  • Boundary markers: SKILL.md explicitly instructs the agent to treat drafts as data and ignore embedded instructions.
  • Capability inventory: The skill executes shell commands via a local Python script and reads/writes local files.
  • Sanitization: No active sanitization of the input text, but the script performs non-executable regex-based analysis.
  • [SAFE]: The skill operates locally, avoids external network calls, and includes privacy-focused design that prevents persistent state unless explicitly requested by the user.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 10, 2026, 12:13 AM