init-deep

Pass

Audited by Gen Agent Trust Hub on Aug 9, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses standard Unix utilities such as find, awk, sed, and wc to analyze project structure, calculate file counts, and measure code density. These operations are performed locally and are strictly for calculating metrics to determine where documentation should be generated.
  • [DATA_EXFILTRATION]: The skill reads existing project documentation files (AGENTS.md and CLAUDE.md) to extract insights and preserve project-specific conventions during updates. These file reads are restricted to the local workspace and are necessary for the skill's primary function.
  • [SAFE]: The skill implements a structured workflow for initializing a knowledge base using platform-native agent spawning tools. No unauthorized network operations, obfuscation, or credential access patterns were detected. All behaviors are consistent with the skill's stated purpose of project documentation management.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 9, 2026, 12:43 PM
Security Audit — agent-trust-hub — init-deep