skill-install-dry-run-planner
Pass
Audited by Gen Agent Trust Hub on Aug 17, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
subprocess.runinscripts/check.pyandscripts/plan_dry_run.pyto execute internal validation scripts and thewagentsCLI tool. - Evidence:
subprocess.run(command, check=False).returncodeinscripts/check.pyandsubprocess.run(command, cwd=REPO_ROOT, text=True, capture_output=True, check=False)inscripts/plan_dry_run.py. - Context: These calls are used to invoke Python-based validation logic and the environment's skill management CLI (
wagents) in a restricted--dry-runmode. The commands are constructed from static lists or controlled arguments, minimizing injection risks. - [PROMPT_INJECTION]: The
evals/evals.jsonfile contains negative test cases specifically designed to ensure the agent refuses to perform live installations even when requested. - Evidence: The
negative-apply-requestandapply-gate-refusalevals verify that the agent declineswagents skills sync --applyornpx skills addcommands, reinforcing the dry-run-only scope of the skill.
Audit Metadata