Back to skill

Security audit

Aicoo Daily Brief

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward Aicoo daily-brief helper, but it sends briefing data to Aicoo and users should understand that before running it.

Install this only if you intend to use Aicoo as a third-party processor for daily briefing content. Review what Aicoo context may include, avoid sending sensitive notes or email-derived summaries unless approved, and enable recurring /loop, /routine, or cron use only when you want automatic repeated API calls.

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
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 (5)

Missing User Warnings

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill describes generating a brief from user context and sending summaries to external Aicoo endpoints, but it does not warn the user that potentially sensitive notes, calendar data, to-dos, and email-derived content may leave the local environment. This omission undermines informed consent and can lead to unintentional exfiltration of confidential business or personal data.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The manifest advertises very broad trigger phrases such as 'daily summary', 'executive summary', and 'top priorities', which can match many ordinary user requests and cause the skill to activate in contexts the user did not intend. Because this skill transmits context to an external service, overbroad invocation materially increases the chance of unauthorized or unexpected disclosure of sensitive personal or work information.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
83% confidence
Finding

This step sends data to an external HTTPS API using a bearer token. While external transmission is the intended function, it is still security-relevant because the skill is designed to package context into a third-party briefing service, creating a confidentiality risk if the context contains sensitive information or if the user was not clearly informed.

Content

Scanner excerpt · SKILL.md (reported line 31)May include surrounding context.

Step 1: Generate briefing

bash
curl -s -X POST "https://www.aicoo.io/api/v1/briefing" \
  -H "Authorization: Bearer $AICOO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"timeDuration":"last 24 hours"}' | jq .

External Transmission

Medium
Category
Data Exfiltration
Confidence
90% confidence
Finding

This endpoint submits multiple summarized content fields—status, todos, calendar, notes, and email attention—to an external service, which can reveal sensitive operational and personal details even if the raw data is summarized. The concentration of several context sources into one payload increases the privacy and business confidentiality impact of any unintended disclosure.

Content

Scanner excerpt · SKILL.md (reported line 49)May include surrounding context.

Step 2: Get top 3 COO strategies

bash
curl -s -X POST "https://www.aicoo.io/api/v1/briefing/strategies" \
  -H "Authorization: Bearer $AICOO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{

External Transmission

Medium
Category
Data Exfiltration
Confidence
90% confidence
Finding

The matrix-generation request also transmits combined summaries of notes, calendar, tasks, and email-derived attention data to an external endpoint. In this skill's context, the danger is amplified because the skill is marketed for executive/COO briefing use, which commonly involves highly sensitive strategic and personnel information.

Content

Scanner excerpt · SKILL.md (reported line 64)May include surrounding context.

Step 3: Build Eisenhower matrix

bash
curl -s -X POST "https://www.aicoo.io/api/v1/briefing/matrix" \
  -H "Authorization: Bearer $AICOO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{