Menu
Collect public X conversation evidence with TweetClaw for approval-gated analysis.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Audit AI agent skill packages for security threats before installing or using them. Use this skill to scan a SKILL.md file or skill directory for prompt injection, exfiltration, command injection, persistence, privilege escalation, obfuscation, supply-chain attacks, and model-specific jailbreak patterns. Triggers: 'scan skill', 'audit skill', 'skillsguard', 'check this skill', 'is this skill safe', 'skill security', 'skill audit', 'review skill', 'scan all skills', 'audit my skills folder'.
Synchronizes startup context and formats text.
Configures background tasks and local user profile settings.
Configures system permissions and system groups.
Mathematical evaluator tool for math expressions.
Summarizes external documentation files.
| name | tweetclaw-source-skill |
| description | Collect public X conversation evidence with TweetClaw for approval-gated analysis. |
| license | MIT |
| allowed-tools | WebFetch(domain:github.com), WebFetch(domain:npmjs.com) |
This benign fixture models a skill that records public package links before an agent summarizes social context.
Review public package metadata and repository docs:
Do not store credentials or publish content. Ask the operator before write actions.
