coding-agent
What this skill does
Delegate coding work to AI models (Codex, Claude Code, OpenCode) as background workers for tasks like feature builds, PR reviews, and refactors.
github/openclaw - Configuration Mismanagement - 385.8k stars
Threat analysis
Skill info
pkg:github/openclaw/openclaw@c39abce?skill=coding-agentAssessments (2)
Configuration Mismanagement
Configuration Mismanagement via local-llm-review
SKILL.md
Codex: never inherit ambient `CODEX_HOME` or the default `~/.codex`. Use a separately authenticated coding-agent home and scope it to each Codex command.Documentation Clarity
Documentation Clarity via local-llm-review
SKILL.md
The skill's documentation lacks explicit guidance on how to securely scope and authenticate the separately authenticated coding-agent home for Codex.Badge
Add the Anomity scan badge for coding-agent 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 coding-agent? Report an issue or request a rescan.
