Security audit

Chirp

Security checks for vulnerabilities and agentic risk

Overview

This skill is not malicious, but it should be reviewed because it can use a logged-in X/Twitter session to take public account actions without consistently requiring confirmation.

Install only if you are comfortable letting an agent operate your logged-in X/Twitter browser session. Before any like, repost, reply, follow, or post, require the agent to show the exact target and content and wait for explicit confirmation.

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
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (3)

Missing User Warnings

Medium

Confidence: 90% confidence
Finding: The skill documents state-changing social actions such as posting, liking, reposting, replying, and following, but only gives explicit confirmation guidance for tweeting. In an agentic context, missing confirmation requirements for these actions increases the risk of unintended account actions, reputation damage, or accidental engagement performed on behalf of the user.

Natural-Language Policy Violations

Low

Confidence: 80% confidence
Finding: The skill description in metadata is in English, while the operational instructions are predominantly in Korean, and the file does not state that the user can choose their preferred language. This can violate language/locale policy expectations by effectively forcing one language for core usage guidance without opt-in.

Description-Behavior Mismatch

Low

Confidence: 96% confidence
Finding: The manifest description limits the skill's stated X/Twitter interactions to reading timeline, posting tweets, liking, retweeting, replying, or searching. The usage section additionally documents following accounts, which is a distinct account-modifying action not mentioned in the manifest scope.

Static analysis

No suspicious patterns detected.