Security audit

News Brief Automation

Security checks for vulnerabilities and agentic risk

Overview

This skill is a transparent Markdown-only helper for creating recurring news digests, with expected workspace file creation and no hidden execution behavior found.

Install this if you want an agent to create reusable news-digest prompts and saved Markdown reports. Before using it, confirm the sources, schedule, report folder, and whether recurring automation in automation/cron/ is appropriate for your workspace.

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 (7)

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 174)May include surrounding context.
md
4. Move concrete examples and templates into `references/` so `SKILL.md` stays lean.

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 180)May include surrounding context.
md
4. Move concrete examples and templates into `references/` so `SKILL.md` stays lean.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill description is broad enough to trigger on common requests like 'check news and send me a summary,' which can cause the agent to invoke this skill in situations the user did not explicitly intend. Over-broad activation increases the chance of unintended automation behavior, unnecessary file creation in the workspace, and unrequested recurring-task setup, especially because the skill is designed to create cron prompts and saved reports.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The example directs the agent to save generated reports into reports/hackernews/YYYY-MM-DD-HH00.md and then send them to the user, but the markdown does not warn that running this workflow will create files in the user's workspace. Because this is a markdown file, omission of a warning about data-affecting behavior falls under missing user warnings.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 91% confidence
Finding: This example explicitly says the skill will save a Markdown report to the workspace and provides a concrete output path, but it does not disclose that the workflow modifies local files. For markdown guidance, user-facing warnings should mention behaviors that affect user data or system state.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 92% confidence
Finding: This markdown template tells the agent to save output into the workspace, which is a user-data-affecting operation. The template does not include any warning or disclosure that it will create or overwrite files in reports/<topic>/, so users may not realize the skill modifies local files.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The daily digest template states that it will save generated output to the workspace and then send it to the user. Because the markdown description lacks an explicit warning about local file creation/modification, the behavior could affect user data without adequate disclosure.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.