Back to skill

Security audit

Tweetnugget

Security checks for vulnerabilities and agentic risk

Overview

TweetNugget is a coherent local quote picker, but its instructions can route a user-supplied topic into a Bash command without clear quoting or validation.

Review before installing if your agent may execute skill-provided Bash snippets automatically. The quote data and Python script are local and simple, but the skill should ideally quote or validate topic inputs, map topics to known tags, or avoid shell interpolation entirely.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Warning
Location
SKILL.md:55
Finding

Shell Command Injection Through Unescaped User-Supplied Topic

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • YARA SignaturesMalware Match, Webshell Match, Cryptominer Match
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (6)

YARA rule 'agent_skill_mcp_tool_poisoning_metadata': MCP/tool metadata poisoning indicators in tool schemas or skill manifests [agent_skills]

High
Category
YARA Match
Confidence
80% confidence
Finding

YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).

Content

Scanner excerpt · README.md (reported line 7)May include surrounding context.

TweetNugget

A random inspirational tweet from hand-picked collections

Curated tweets from tech leaders, founders, and philosophers — wisdom from Twitter/X delivered exactly when you need it.

ClawHub License: MIT Version Quote Count

Install

ClawHub (recommended)

bash
clawhub install tweetnugget

Browse on [clawhub.dev/tweetnugget](https://

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The quick-start phrases are generic everyday requests like 'Give me a quote' and 'Surprise me', which are likely to match ordinary conversation outside an explicit invocation flow. In an agent-skill environment, overly broad triggers can cause unintended activation, leading to unsolicited skill execution and response hijacking when the user did not specifically intend to invoke this skill.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger phrases are broad conversational language such as asking for inspiration or wisdom, which can cause the skill to activate in situations the user did not specifically intend. Unintended invocation can override more appropriate handling, produce irrelevant output, or unexpectedly execute the associated tool flow, especially in agents that auto-route based on natural language heuristics.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

This JSON file contains natural-language content, and the quote at L443 explicitly frames the statement as applying to 'Men' only. Under the language/locale policy category, this is a natural-language phrasing choice that imposes a gendered framing without justification or opt-in.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
98% confidence
Finding

At L152 the code uses "" in t, which is true for every string in Python, including non-empty tag values. The comments at L153-L154 explicitly state the opposite and therefore actively contradict the implemented behavior.

Content

No source excerpt is available for this finding.