ClawHub
Back to skill

Security audit

My Life Feed

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward MyFeed API helper, but users should understand that it can send real invitations and reminders to other people.

Install only if you trust MyFeed with your API key and the event, group, and phone-number data you submit. Before using friend or group invites, verify the recipient or group ID and make sure you are allowed to share that phone number and send reminders.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (7)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The README states that friends receive reminders from My Life Feed things, but it does not present this as a user-facing warning about the consequences of using the skill. Without a prominent warning, users may not realize that their actions in the skill can generate notifications to friends or groups, which can lead to accidental spam, social engineering opportunities, or unintended disclosure of relationship/group context.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The README explicitly describes inviting specific friends or groups and selecting them using phone numbers, but it does not warn users that operating the skill can contact third parties or involve contact-based personal data. This is dangerous because users may trigger reminders or invitations affecting other people without understanding the privacy and consent implications, increasing the risk of unintended outreach or misuse of others' phone numbers.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
92% confidence
Finding

The skill is explicitly built to send data to an external REST API, including descriptions, timestamps, group identifiers, phone numbers, and an API key-bearing authorization header. External transmission is expected for this skill, but it remains security-relevant because sensitive account and personal data leave the local environment and the documentation provides little guidance on privacy, consent, or secure secret handling.

Content

Scanner excerpt · SKILL.md (reported line 22)May include surrounding context.

md
## Usage

All commands use curl to hit the My Life Feed REST API.

### Create thing and invite a friend

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The documented API call sends personal data, including a friend's phone number and account-scoped API credentials, to an external service without an explicit privacy notice or guidance on consent, minimization, or handling of recipient data. In a skill designed to invite other people, this increases the risk of users transmitting third-party personal data without understanding the privacy implications.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
89% confidence
Finding

This example sends event metadata and group invitation information to the external MyFeed API using an account-wide API key. While this is core functionality rather than obviously malicious behavior, it still creates real exposure if users do not understand that group identifiers and account actions are being transmitted and can affect other people.

Content

Scanner excerpt · SKILL.md (reported line 59)May include surrounding context.

Create thing and invite a group

bash
curl -X POST https://skill.myfeed.life/api -H "Authorization: ApiKey $Myfeed_API_KEY" -H "Content-Type: application/json" 
-d '{"request":"create_thing",
 "params":{
   "description":"Thing description",

External Transmission

Medium
Category
Data Exfiltration
Confidence
90% confidence
Finding

This example demonstrates sending invitations and reminder data, potentially including third-party phone numbers or group information, to an external service. In context, the transmission is intentional and aligned with the skill's purpose, but it is more sensitive than generic outbound traffic because it involves personal contact data and account-authorized actions affecting others.

Content

Scanner excerpt · SKILL.md (reported line 95)May include surrounding context.

md
}
}'| jq '.groups[] | select(.group|contains ("friends"))'
# Add a thing and invite a group. When you invite a group, you can't invite other people. You are adding 2 reminders before the thing time in this invite: one with 10 minutes ahead and one with 4 hours. You are adding the thing for the group with the group_id 564564646. The thing time is 1770935248000. Start time needs to be in the future.
curl -X POST https://skill.myfeed.life/api -H "Authorization: ApiKey $Myfeed_API_KEY" -H "Content-Type: application/json" 
-d '{"request":"create_thing",
 "params":{
   "description":"Thing description",

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

The text requires users to provide phone numbers in a fixed format of country prefix plus number with no '+' sign, which imposes a formatting/locale convention in natural-language instructions. The file does not explain whether this is an API-imposed requirement or provide alternatives or guidance for users in different locales.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.