Tweet Crafter
Security checks across static analysis, malware telemetry, and agentic risk
Overview
This skill appears to draft marketing text only, with a disclosed Agent Swarm dependency that users should verify before relying on it.
This looks safe for drafting tweets and blog posts, but review the separate Agent Swarm setup before use and avoid putting private or unreleased information into prompts unless you trust that routing path.
Static analysis
No static analysis findings were reported for this release.
VirusTotal
No VirusTotal findings for this skill version.
- Malicious
- 0
- Suspicious
- 0
- Harmless
- 0
- Undetected
- 65
Risk analysis
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
The main behavior may depend on a separately installed Agent Swarm component, which has its own trust and security profile.
The skill depends on another skill or local component for its advertised LLM routing, but that dependency is not part of the provided install spec.
Ensure you have Agent Swarm (workspace/skills/agent-swarm or clawhub install agent-swarm) configured and enabled
Install Agent Swarm only from a trusted source and review that skill separately before using this integration.
If connected to Agent Swarm, draft prompts and blog context may be passed into another agent or provider workflow.
The code is designed around routing the user's prompt and blog context through a separate Agent Swarm component, even though the current implementation returns mocked content.
AGENT_SWARM_SCRIPT = os.path.join(... "agent-swarm", "scripts", "router.py")
Use this skill with non-sensitive marketing content, and confirm how Agent Swarm routes, stores, or forwards prompts before including confidential information.