Security audit

Daily Briefing

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent productivity briefing template, with expected but privacy-sensitive data sharing and optional persistence that users should configure carefully.

Install only if you are comfortable letting your agent read the configured calendar, task, location/weather, and optional news or inbox sources and send summaries to your chosen messaging channel. Keep BRIEFING.md narrow, avoid sensitive calendar/task details where possible, review any cron or heartbeat automation, and enable memory logging only if you want persistent briefing/task history.

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 (4)

Missing User Warnings

Medium

Confidence: 93% confidence
Finding: The skill explicitly aggregates calendar entries, tasks, weather/location, pending items, and optionally news, then sends the compiled briefing to external messaging channels. Without a clear privacy warning or consent guidance, users may unknowingly enable transmission of sensitive personal or work data to third-party services and integrations.

Vague Triggers

Medium

Confidence: 88% confidence
Finding: The invocation guidance says users can trigger the skill by saying "Give me my daily briefing," but the file does not define boundaries or exclusions for similar natural-language requests. In a manifest/markdown skill description, this kind of generic phrasing can overlap with ordinary conversation and lead to unintended activation.

Missing User Warnings

Low

Confidence: 88% confidence
Finding: The document explicitly instructs the agent to log briefing engagement to `memory/briefing-log.json`, which creates persistent behavioral metadata about the user without mentioning consent, retention, or visibility. While not overtly malicious, this can expose routine patterns and task sensitivity if stored locally and later accessed by other skills, users, or processes.

Missing User Warnings

Low

Confidence: 91% confidence
Finding: The memory integration section describes a continuous read/write loop over daily memory files containing tasks and status, but it does not warn that user task data will persist across days. This creates an ongoing accumulation of potentially sensitive personal productivity data, increasing exposure if the memory store is shared, synced, or later processed beyond the user's expectations.

Static analysis

No suspicious patterns detected.