specclaw
What this skill does
SpecClaw is a spec-driven development framework for OpenClaw agents. It helps manage the full lifecycle of feature development, from proposing features to verifying implementations.
github/leoyeai - Excessive Agency - 2.1k stars
Threat analysis
Skill info
pkg:github/LeoYeAI/openclaw-master-skills@e5199b5?skill=specclawAssessments (2)
Excessive Agency
Excessive Agency via local-llm-review
SKILL.md
The skill allows agents to 'spawn coding agents' and 'validate implementations' without explicit verification or user confirmation.Potential Misuse
Potential Misuse via local-llm-review
scripts/build-context.sh
The script builds context payloads for coding agents, which could be used to execute arbitrary code if not properly constrained.Badge
Add the Anomity scan badge for specclaw 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 specclaw? Report an issue or request a rescan.
