feishu-doc-collab
What this skill does
Enable real-time AI collaboration in Feishu (Lark) documents by detecting edits and triggering isolated agent sessions.
github/leoyeai - Code Injection - 2.1k stars
Threat analysis
Skill info
pkg:github/LeoYeAI/openclaw-master-skills@e5199b5?skill=feishu-doc-collabAssessments (2)
Code Injection
Code Injection via local-llm-review
scripts/patch-monitor.sh
The script patches OpenClaw's Feishu extension (`monitor.ts`) to trigger an agent turn on document edit events. It reads configuration from `openclaw.json` and sends data to a local endpoint (`http://Configuration Dependency
Configuration Dependency via local-llm-review
scripts/patch-monitor.sh
The script depends on `openclaw.json` being configured with a `hooks.token` and `gateway.port`. If these are not properly secured, they could be exploited.Badge
Add the Anomity scan badge for feishu-doc-collab 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 feishu-doc-collab? Report an issue or request a rescan.
