distill-skill

Pass

Audited by Gen Agent Trust Hub on Jul 17, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses shell commands to manage temporary directories and trace files in a dedicated scratch space ($PRAXIS_DIR/.tmp/). These operations are scoped to session management and do not involve untrusted input or risky network operations.
  • [SAFE]: The skill delegates final file creation to an external 'edit-tool', preventing it from writing executable content or skill files directly to the filesystem, which is a strong security boundary.
  • [SAFE]: Instructions include mandatory deduplication checks ('search-skill') before proposing new skill creation, reducing the risk of redundant or conflicting skill definitions.
  • [SAFE]: All network-like operations (search, edit, kaizen) use predefined internal tools rather than raw network utilities like curl or wget.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 17, 2026, 12:04 PM
Security Audit — agent-trust-hub — distill-skill