Media Bias News

• Outcome: Pass
• Latest audit: Sep 16, 2026 · 11:16 AM UTC
• Version: 0.1.0

Overview

This is a coherent news and media-bias lookup skill that makes disclosed read-only requests to MediaBias.news and does not show hidden local access, persistence, or destructive behavior.

Install only if you are comfortable with news queries, outlet names, domains, and article URLs being sent to MediaBias.news for analysis. Because the skill may handle generic news prompts, use a project-scoped install if you want tighter control over when it is available.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (4)

Skill Enumeration

Medium

• Category: Agent Snooping
• Confidence: 80% confidence

Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · README.md (reported line 115)May include surrounding context.

md

| Agent | Where the file goes |
|---|---|
| Claude Code, Claude Desktop | `~/.claude/skills/media-bias-news/SKILL.md`, or `.claude/skills/media-bias-news/` in a project |
| Codex | append the body to `AGENTS.md` at the repo root |
| Cursor | `.cursor/rules/media-bias-news.mdc` |
| Windsurf | `.windsurf/rules/media-bias-news.md` |

Skill Enumeration

Medium

• Category: Agent Snooping
• Confidence: 80% confidence

Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · SKILL.md (reported line 194)May include surrounding context.

md

| Agent | Where the file goes |
|---|---|
| Claude Code, Claude Desktop | `~/.claude/skills/media-bias-news/SKILL.md`, or `.claude/skills/media-bias-news/` in a project |
| Codex | append the body to `AGENTS.md` at the repo root |
| Cursor | `.cursor/rules/media-bias-news.mdc` |
| Windsurf | `.windsurf/rules/media-bias-news.md` |

Skill Enumeration

Medium

• Category: Agent Snooping
• Confidence: 80% confidence

Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · SKILL.md (reported line 195)May include surrounding context.

md

| Agent | Where the file goes |
|---|---|
| Claude Code, Claude Desktop | `~/.claude/skills/media-bias-news/SKILL.md`, or `.claude/skills/media-bias-news/` in a project |
| Codex | append the body to `AGENTS.md` at the repo root |
| Cursor | `.cursor/rules/media-bias-news.mdc` |
| Windsurf | `.windsurf/rules/media-bias-news.md` |

Vague Triggers

Medium

• Category: Not specified by scanner
• Confidence: 95% confidence

Finding

The skill advertises very broad trigger phrases such as 'what's happening today', 'summarise this story', and pasted URLs, which can overlap with many ordinary user requests. In agent environments that auto-select skills from natural-language descriptions, this can cause over-invocation of the skill, unnecessary external requests, and unintended routing of user content to a third-party API.

Content

No source excerpt is available for this finding.