harness-plan

Pass

Audited by Gen Agent Trust Hub on Jul 30, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes standard command-line utilities such as git, gh, and jq for repository management and GitHub issue creation. These actions are consistent with the skill's primary function of planning and tracking project milestones.
  • [DYNAMIC_EXECUTION]: The skill invokes local shell scripts (e.g., foundation-readiness.sh) within the project's .harness/scripts/ directory to perform environment checks. This execution is scoped to project-resident scripts initialized in prior setup steps.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted data from git log and user inputs. It addresses this risk through architectural safeguards, including the use of specialized wrapping for untrusted content and clear role definitions for sub-agents to distinguish between data and instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 30, 2026, 07:28 AM
Security Audit — agent-trust-hub — harness-plan