skills/mickeyyaya/evolve-loop/release/Gen Agent Trust Hub

release

Pass

Audited by Gen Agent Trust Hub on Jun 21, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill interpolates the user-provided argument directly into shell command strings, such as $CLAUDE_PROJECT_DIR/go/bin/evolve release-preflight --dry-run. This creates a command injection surface.
  • Ingestion points: The version argument supplied by the user in the skill invocation (SKILL.md).
  • Boundary markers: No escaping, shell-safe delimiters, or ignore-embedded-instruction warnings are specified for the interpolation.
  • Capability inventory: The skill executes local binaries and standard development tools including git and gh (SKILL.md).
  • Sanitization: No input validation or sanitization logic is described to ensure the target string does not contain shell metacharacters.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 21, 2026, 06:39 AM
Security Audit — agent-trust-hub — release