Security audit

TweetClaw

Security checks for vulnerabilities and agentic risk

Overview

TweetClaw is a clearly disclosed X/Twitter automation plugin with sensitive capabilities, but its artifacts show approval gates, route limits, and credential handling that fit its stated purpose.

Install only if you are comfortable giving an OpenClaw plugin access to an Xquik API key or MPP signing key for your authorized X/Twitter workflows. Review each approval prompt carefully, especially for posts, deletes, DMs, exports, monitors, and paid calls, and disable polling if you do not want monitor event checks.

SkillSpector

Vulnerability Patterns

Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

Autonomous Decision Making

Medium

Category: Excessive Agency
Confidence: 75% confidence
Finding: Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
Content: Scanner excerpt · skills/tweetclaw/evals/evals.json (reported line 29)May include surrounding context.
json
"wait for explicit approval" ], "must_not_include": [ "post without approval", "batch write" ] },

Static analysis

Detected: suspicious.install_untrusted_source

Install source points to URL shortener or raw IP.

Warn

Code: suspicious.install_untrusted_source
Location: generated-api-contract.json:431
Evidence: {"name":"urls","in":"query","required":true,"type":"string","description":"1 to 100 links of the form `https://t.co/Xe1nm2pkSX`, separated by commas. Any other ...