Back to skill

Security audit

UseMemos

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent UseMemos helper, but it encourages and permits sending a bearer token and private memo data over plaintext HTTP, including with long-lived tokens.

Install only if you are comfortable granting this skill access to your UseMemos account. Use HTTPS for USEMEMOS_URL, avoid non-expiring tokens, keep the .env file private, rotate/revoke the token if exposed, and be careful with delete/comment operations because they mutate remote memo data.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Error
Location
SKILL.md:23
Finding

Bearer Tokens and Private UseMemos Content Can Be Transmitted over Plaintext HTTP

Content
View full analysis
My Account > Access Tokens, create one there, do not forget to assign expiration (i use Never to avoid troubles, but hey there are also arguments against that) ``` The scripts then send that bearer token and user data directly to the configured URL without validating its scheme. For example, `scripts/upload_attachment.py:40-52` contains: ```python req = urllib.request.Request( f"{base_url}/api/v1/attachments", data=payload, headers={ 'Authorization': f'Bearer {token}', 'Content-Type': 'application/json', 'Accept': 'application/json' }, method='POST' ) try: with urllib.request.urlopen(req) as resp: data = json.loads(resp.read().decode()) ``` Similarly, the common request logic in `scripts/memo_comments.py:27-39` is: ```python def api_request(base_url, token, path, method='GET', data=None): body = json.dumps(data).encode() if data else None req = urllib.request.Request( f"{base_url}{path}", data=body, headers={ 'Authorization': f'Bearer {token}', 'Content-Type': 'appli ...[truncated 3059 chars]
Remediation
View remediation
Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (49)

Tainted flow: 'req' from os.environ.get (line 32, credential/environment) → urllib.request.urlopen (network output)

Critical
Category
Data Flow
Confidence
90% confidence
Finding

Credentials or environment variables flow to a network sink. This is a high-confidence indicator of credential exfiltration.

Content

Scanner excerpt · scripts/create_memo.py (reported line 44)May include surrounding context.

python
)

    try:
        with urllib.request.urlopen(req) as resp:
            data = json.loads(resp.read().decode())
            memos = data.get('memos', [])
            if not memos:

Tainted flow: 'req' from os.environ.get (line 32, credential/environment) → urllib.request.urlopen (network output)

Critical
Category
Data Flow
Confidence
90% confidence
Finding

Credentials or environment variables flow to a network sink. This is a high-confidence indicator of credential exfiltration.

Content

Scanner excerpt · scripts/list_memos.py (reported line 41)May include surrounding context.

python
)

    try:
        with urllib.request.urlopen(req) as resp:
            data = json.loads(resp.read().decode())
            memos = data.get('memos', [])
            if not memos:

Tainted flow: 'req' from os.environ.get (line 40, credential/environment) → urllib.request.urlopen (network output)

Critical
Category
Data Flow
Confidence
90% confidence
Finding

Credentials or environment variables flow to a network sink. This is a high-confidence indicator of credential exfiltration.

Content

Scanner excerpt · scripts/search_memos.py (reported line 49)May include surrounding context.

python
)

    try:
        with urllib.request.urlopen(req) as resp:
            data = json.loads(resp.read().decode())
            memos = data.get('memos', [])
            if not memos:

Tainted flow: 'req' from os.environ.get (line 40, credential/environment) → urllib.request.urlopen (network output)

Critical
Category
Data Flow
Confidence
90% confidence
Finding

Credentials or environment variables flow to a network sink. This is a high-confidence indicator of credential exfiltration.

Content

Scanner excerpt · scripts/upload_attachment.py (reported line 52)May include surrounding context.

python
)

    try:
        with urllib.request.urlopen(req) as resp:
            data = json.loads(resp.read().decode())
            memos = data.get('memos', [])
            if not memos:

Tainted flow: 'req' from os.environ.get (line 102, credential/environment) → urllib.request.urlopen (network output)

Critical
Category
Data Flow
Confidence
90% confidence
Finding

Credentials or environment variables flow to a network sink. This is a high-confidence indicator of credential exfiltration.

Content

Scanner excerpt · scripts/upload_and_link_attachment.py (reported line 61)May include surrounding context.

python
)

    try:
        with urllib.request.urlopen(req) as resp:
            attachment = json.loads(resp.read().decode())
    except urllib.error.HTTPError as e:
        print(f"Upload failed: {e.code} - {e.read().decode()}", file=sys.stderr)

Tainted flow: 'req' from os.environ.get (line 102, credential/environment) → urllib.request.urlopen (network output)

Critical
Category
Data Flow
Confidence
90% confidence
Finding

Credentials or environment variables flow to a network sink. This is a high-confidence indicator of credential exfiltration.

Content

Scanner excerpt · scripts/upload_and_link_attachment.py (reported line 110)May include surrounding context.

python
)

    try:
        with urllib.request.urlopen(req) as resp:
            attachment = json.loads(resp.read().decode())
    except urllib.error.HTTPError as e:
        print(f"Upload failed: {e.code} - {e.read().decode()}", file=sys.stderr)

Tainted flow: 'get_req' from os.environ.get (line 76, credential/environment) → urllib.request.urlopen (network output)

Critical
Category
Data Flow
Confidence
90% confidence
Finding

Credentials or environment variables flow to a network sink. This is a high-confidence indicator of credential exfiltration.

Content

Scanner excerpt · scripts/upload_and_link_attachment.py (reported line 83)May include surrounding context.

python
)

    try:
        with urllib.request.urlopen(get_req) as resp:
            memo_data = json.loads(resp.read().decode())
    except urllib.error.HTTPError as e:
        print(f"Failed to get memo: {e.code} - {e.read().decode()}", file=sys.stderr)

Tainted flow: 'req' from os.environ.get (line 109, credential/environment) → urllib.request.urlopen (network output)

Critical
Category
Data Flow
Confidence
90% confidence
Finding

Credentials or environment variables flow to a network sink. This is a high-confidence indicator of credential exfiltration.

Content

Scanner excerpt · tests/test_image_upload.py (reported line 91)May include surrounding context.

python
req = urllib.request.Request(
        f'{BASE_URL}{path}', data=body, headers=headers, method=method,
    )
    with urllib.request.urlopen(req) as resp:
        return json.loads(resp.read().decode())

Tainted flow: 'req' from os.environ.get (line 109, credential/environment) → urllib.request.urlopen (network output)

Critical
Category
Data Flow
Confidence
90% confidence
Finding

Credentials or environment variables flow to a network sink. This is a high-confidence indicator of credential exfiltration.

Content

Scanner excerpt · tests/test_image_upload.py (reported line 112)May include surrounding context.

python
req = urllib.request.Request(
        f'{BASE_URL}{path}', data=body, headers=headers, method=method,
    )
    with urllib.request.urlopen(req) as resp:
        return json.loads(resp.read().decode())

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · README.md (reported line 28)May include surrounding context.

  1. Copy the example environment file and fill in your values:
bash
cp .env.example .env
  1. Edit .env with your UseMemos instance URL and access token:

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

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

cp .env.example .env

text

2. Edit `.env` with your UseMemos instance URL and access token:

USEMEMOS_URL=http://localhost:5230

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · README.md (reported line 38)May include surrounding context.

cp .env.example .env

text

2. Edit `.env` with your UseMemos instance URL and access token:

USEMEMOS_URL=http://localhost:5230

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The declared description omits comment management and especially comment deletion, which is a destructive capability. This mismatch can mislead users and reviewers about what actions the skill may take, creating a risk of unauthorized or unexpected data modification in the UseMemos instance.

Content

No source excerpt is available for this finding.

Credential Access

High
Category
Privilege Escalation
Confidence
92% confidence
Finding

The skill workflow centers on obtaining and storing an access token, and the text explicitly suggests using a token that never expires. In the context of a network-enabled skill that performs authenticated actions against a self-hosted memo system, compromise of that token could allow persistent unauthorized access, data exfiltration, and destructive operations.

Content

Scanner excerpt · SKILL.md (reported line 29)May include surrounding context.

USEMEMOS_TOKEN=your_access_token_here

text

Get your ```USEMEMOS_TOKEN``` from UseMemos instance, login and go to: **Settings > My Account > Access Tokens**, create one there, do not forget to assign expiration (i use **Never** to avoid troubles, but hey there are also arguments against that)

**Note:** All scripts automatically load the `.env` file from the skill directory. No need to export variables manually.

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
80% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · references/api.md (reported line 70)May include surrounding context.

Delete Memo

text
DELETE /api/v1/memos/{id}

Comments

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
80% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · references/api.md (reported line 107)May include surrounding context.

Use the standard delete memo endpoint with the comment's memo ID:

text
DELETE /api/v1/memos/{comment_id}

Attachments

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
80% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · references/api.md (reported line 145)May include surrounding context.

Delete Attachment

text
DELETE /api/v1/attachments/{id}

Tags

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · scripts/create_memo.py (reported line 9)May include surrounding context.

python
#!/usr/bin/env python3
"""Load .env file from the skill directory."""
import os
import sys
from pathlib import Path

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · scripts/list_memos.py (reported line 10)May include surrounding context.

python
#!/usr/bin/env python3
"""Load .env file from the skill directory."""
import os
import sys
from pathlib import Path

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · scripts/load_env.py (reported line 2)May include surrounding context.

python
#!/usr/bin/env python3
"""Load .env file from the skill directory."""
import os
import sys
from pathlib import Path

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · scripts/load_env.py (reported line 8)May include surrounding context.

python
#!/usr/bin/env python3
"""Load .env file from the skill directory."""
import os
import sys
from pathlib import Path

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · scripts/memo_comments.py (reported line 16)May include surrounding context.

python
#!/usr/bin/env python3
"""Load .env file from the skill directory."""
import os
import sys
from pathlib import Path

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · scripts/search_memos.py (reported line 10)May include surrounding context.

python
#!/usr/bin/env python3
"""Load .env file from the skill directory."""
import os
import sys
from pathlib import Path

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · scripts/upload_and_link_attachment.py (reported line 11)May include surrounding context.

python
#!/usr/bin/env python3
"""Load .env file from the skill directory."""
import os
import sys
from pathlib import Path

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · scripts/upload_attachment.py (reported line 10)May include surrounding context.

python
#!/usr/bin/env python3
"""Load .env file from the skill directory."""
import os
import sys
from pathlib import Path