milestone-runner

Pass

Audited by Gen Agent Trust Hub on Aug 1, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [SAFE]: No malicious patterns, data exfiltration, or obfuscation were detected. The skill's operations are consistent with its documented purpose of development orchestration.\n- [PROMPT_INJECTION]: The skill processes instructions from documentation files, creating an indirect prompt injection surface.\n
  • Ingestion points: .docs/DEVELOPMENT_PLAN.md and .docs/EXECUTION_PROMPTS.md.\n
  • Boundary markers: Instructions are delimited by /goal blocks.\n
  • Capability inventory: The skill invokes omp, stacked-prs, and ship-workflow tools.\n
  • Sanitization: Requires a mandatory 'DESIGN GO' gate and reviewed reconciliation PRs before implementation.\n- [COMMAND_EXECUTION]: The skill triggers shell commands via the omp utility using content extracted from local files at runtime.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 1, 2026, 09:23 PM
Security Audit — agent-trust-hub — milestone-runner