Security audit

Global News By Opera News

Security checks for vulnerabilities and agentic risk

Overview

This news skill is review-worthy because it asks the agent to run shell-based web requests with user-influenced inputs and to display third-party news content as safe without enough validation.

Install only if you are comfortable with the skill making external requests to the Opera News feed and with your agent using Bash for those requests. Prefer a version that uses a scoped HTTP tool, validates country/language codes, safely URL-encodes all user-controlled fields, checks returned links before displaying them, and asks before assuming a default locale.

A.I.G

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 (2)

T09 · Insecure Skill Coding Practices

Error

Location: SKILL.md:109
Finding: Potential Shell Command Injection Through User-Derived API Parameters
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Warning

Location: SKILL.md:245
Finding: Untrusted Remote News Content Is Declared Safe for Direct Rendering
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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 (3)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger list contains very broad terms such as "news," "video," and "what's happening," which are likely to overlap with normal user conversation and unrelated intents. This can cause unintended skill activation and routing of user requests to this skill when the user did not explicitly ask for it, increasing the chance of inappropriate data fetching or user confusion.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: Defaulting to us/en when the user's market is unclear can cause the system to infer or impose a locale without explicit user choice. While not a code-execution issue, it can lead to privacy and relevance concerns by returning location- or language-specific content the user did not request.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The explicit instruction to always fall back to us/en reinforces behavior that selects a specific locale without user consent. This makes accidental mis-targeting systematic across the skill and may expose users to irrelevant or culturally incorrect content, especially for non-US users.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.