Security audit

A3 Interest Watchlist

Security checks for vulnerabilities and agentic risk

Overview

Scanners returned a benign verdict, with no AIG findings and one low-probability Skillspector finding judged consistent with the stated briefing purpose; coverage was partial.

The verdict is benign, but it is not a guarantee of safety. Skillspector inspected 2 of 3 components; the executable watchlist.mjs was only partially inspected because its contents could not be fully interpreted. Consider that uncertainty before installing.

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

Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
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 (1)

Autonomous Decision Making

Medium

Category: Excessive Agency
Confidence: 80% confidence
Finding: Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
Content: Scanner excerpt · SKILL.md (reported line 6)May include surrounding context.
md
description: Build a short source-linked briefing for gaming, AI, Salesforce/company news, politics, and YouTube interests, with dated sources and duplicate/material-change checks. --- An explicit request for a fresh read-only preview is already permission to search and prepare it. Execute it directly; do not ask the user to confirm a preview. A preview does not send news or mark it reported. Read topics.json for configurable interests. Use the configured free web_search provider to gather candidates. Start with the user's requested categories; for a full briefing cover the configured topics using bounded searches. Prefer original publisher, company, government or creator statements. For Deadlock/Valorant patch or event coverage, use the configured official source hosts; a newly dated secondary article does not verify a new official update. Fetch the original source with web_fetch when search metadata does not establish its actual publication/update date. If the original source/date c