openclaw-video-toolkit
What this skill does
A video creation toolkit that uses AI models for voiceovers, image generation, music, and animation, with Remotion for rendering. It runs on cloud GPUs via Modal or RunPod.
github/digitalsamba - Path Manipulation Risk - 1.9k stars
Threat analysis
Skill info
pkg:github/digitalsamba/claude-code-video-toolkit@9826feb?skill=openclaw-video-toolkitAssessments (2)
Path Manipulation Risk
Path Manipulation Risk via local-llm-review
SKILL.md
The skill instructs users to always `cd` into a fixed path (`~/.openclaw/workspace/claude-code-video-toolkit`) before running any tool command. This could be a risk if the path is not properly validatCommand Injection Risk
Command Injection Risk via local-llm-review
SKILL.md
The skill includes examples of commands that use user-provided inputs (e.g., `--preset`, `--duration`, `--output`). If these inputs are not properly sanitized, they could be exploited for command injeBadge
Add the Anomity scan badge for openclaw-video-toolkit 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 openclaw-video-toolkit? Report an issue or request a rescan.
