install-anti-slop-py

Pass

Audited by Gen Agent Trust Hub on Aug 26, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local Python script scripts/install.py to vendor the linter package into the current repository. This is the intended behavior for deploying the tool locally.
  • [DYNAMIC_EXECUTION]: The linter engine uses importlib.import_module in assets/anti_slop/engine/config.py to load internal "contrib" rule groups. This dynamic loading is strictly gated by a hardcoded list of known groups (KNOWN_GROUPS), preventing the execution of arbitrary or untrusted modules.
  • [DYNAMIC_CODE_GENERATION]: The installer generates a small Python launcher (__main__.py) in the target directory. The generated code is a standard wrapper that performs a Python version check and imports the local anti_slop package.
  • [INDIRECT_PROMPT_INJECTION]: The skill includes an attack surface for indirect prompt injection as it processes local Python files and parses comments for linter directives (e.g., # anti-slop: ignore[...]). However, the linter only uses these comments to toggle internal logic and does not execute content from these comments or pass them to an LLM context in a way that allows for instruction override.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 26, 2026, 02:49 PM
Security Audit — agent-trust-hub — install-anti-slop-py