ClawHub
Back to skill

Security audit

X API

Security checks for vulnerabilities and agentic risk

Overview

This is a read-only documentation skill for a paid third-party X/Twitter data API, with some wording that users should treat carefully before making calls.

Install only if you intentionally want an agent to retrieve X/Twitter data through twitter.fetcher.sh. Treat the API key as a secret, expect each call to contact a third-party paid service, and avoid sending sensitive or confidential queries unless you are comfortable with that provider receiving them.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The description uses broad capability language such as social listening, competitor monitoring, hashtag tracking, and follower export, which can cause an agent to select this skill for loosely related requests that merely mention X/Twitter data. In an automated tool-selection pipeline, that overbroad routing can lead to unnecessary external data access, unintended paid API calls, and use of a third-party scraping/data service when the user did not clearly request it.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger condition 'If your task mentions an X search query, a handle, a post/tweet ID, or a list ID, this is the skill' is an overly aggressive routing rule. A mere mention of those artifacts does not imply user consent to query an external paid service, so an agent could invoke this skill in contexts where X data lookup is incidental, causing scope creep, privacy issues, or unexpected charges.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

This markdown file instructs users to export an API key and send it in Authorization headers for repeated curl requests, but it does not include any warning about protecting the token, shell history exposure, or the fact that requests send authenticated data to an external service. For markdown files, SQP-2 applies when descriptions omit warnings about behaviors that could affect user data, privacy, or system integrity.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

The document instructs users to send authenticated requests and payment-bearing traffic to an external service without clearly warning that search terms, handles, IDs, and other request data will be transmitted off-platform. In a skill context, users may assume local or first-party processing; this can lead to unintended disclosure of sensitive queries or operational metadata to the third-party API provider.

Content

No source excerpt is available for this finding.

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
references/scenarios.md:11

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
SKILL.md:80