plan-eng-review
What this skill does
Eng manager-mode plan review. Lock in the execution plan - architecture, data flow, diagrams, edge cases, test coverage, performance. Walks through issues interactively with opinionated recommendation
github/leoyeai - Command Execution - 2.1k stars
Threat analysis
Skill info
pkg:github/LeoYeAI/openclaw-master-skills@e5199b5?skill=plan-eng-reviewAssessments (3)
Command Execution
Command Execution via local-llm-review
SKILL.md
The skill executes shell commands such as `mkdir -p ~/.gstack/sessions`, `touch ~/.gstack/sessions/"$PPID"`, and `find ~/.gstack/sessions -mmin +120 -delete`. This could be used to manipulate the fileEnvironment Variable Access
Environment Variable Access via local-llm-review
SKILL.md
The skill accesses environment variables such as `$_UPD`, `$_CONTRIB`, and `$_BRANCH`. This could be used to gather information about the user's environment or to inject malicious code.File System Access
File System Access via local-llm-review
SKILL.md
The skill contains Bash code that creates directories and files in the user's home directory (~/.gstack/sessions). This could be used to store session data or potentially malicious files.Badge
Add the Anomity scan badge for plan-eng-review to your README.
How Anomity governs this at runtime
Scan-time vetting tells you what a skill says it will do. Anomity's Endpoint Sensor sees what agents actually do: it discovers skills alongside every other AI artifact on the endpoint, and runtime governance can allow, deny, or log the tool calls a skill triggers. Policy violations route to your SIEM, Slack, email, or Jira, backed by a queryable 90-day audit trail.
Book a 30-minute demo to see your own skill inventory.
Methodology and disputes
Every skill is assessed by the Anomity Skill Intelligence engine against its public source; findings indicate risk patterns, not confirmed exploitation. Maintainer of plan-eng-review? Report an issue or request a rescan.
