do
What this skill does
Feature development workflow orchestrator using codeagent-wrapper to manage a 5-phase development process (Understand, Clarify, Design, Implement, Complete).
github/stellarlinkco - Agent Snooping - 2.7k stars
Threat analysis
Skill info
pkg:github/stellarlinkco/myclaude@f2e75c1?skill=doAssessments (2)
Agent Snooping
Agent Snooping via local-llm-review
README.md
References to ~/.claude/settings.json and ~/.codeagent/agents/ directory which could be used to inject custom agent behaviorCode Injection
Code Injection via local-llm-review
hooks/verify-loop.py
Use of shell=True in subprocess.run() could be exploited for code injection if cmd variable is not properly sanitizedBadge
Add the Anomity scan badge for do 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 do? Report an issue or request a rescan.
