tao-context-mode
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill documents a Python API for codebase indexing (
build_index,expand) designed to reduce context window usage. - [SAFE]: The summarization logic is stated to be algorithmic (pure regex and first-comment synopsis) with no LLM calls, which significantly reduces risks associated with indirect prompt injection during the indexing phase.
- [SAFE]: No network operations, sensitive data exfiltration patterns, or obfuscated content were detected in the provided documentation.
- [SAFE]: The execution of a local validation script (
scripts/validate_tao_context_mode.py) is standard practice for infrastructure skills and does not involve remote downloads or untrusted code execution.
Audit Metadata