taskr

SAFE max severity MEDIUMSkillSpector Safe 7 registry clawhub.ai last scanned 2026-02-07 1 scan

Verdict safe, but 6 findings (2 medium, 4 low), mainly social engineering, data exfiltration, policy violation. Most recent scan 2026-02-07.

The Taskr skill presents MODERATE security concerns primarily related to data transmission and credential management. The skill functions as a cloud-based task tracking system that sends project data to an external API (taskr.one) without explicit user consent or privacy disclosures. While the service appears legitimate, users may unknowingly transmit sensitive project information, code context, and work patterns to third-party servers. The API key management approach stores credentials in configuration files without security guidance, creating exposure risks. The skill lacks critical metadata (license, compatibility) and has incomplete setup instructions. However, no active malicious behavior, prompt injection, or code execution vulnerabilities were detected. The skill appears to function as described, but requires better transparency about data handling and security practices.
Scanner's overall assessment (LLM analyzer)

Findings6

Critical0

High0

Medium2

Low4

Analyzersstatic llm meta

Second scanner: NVIDIA SkillSpector

VerdictSafe 7

Score7 / 100

Issues1

CategoriesExcessive Agency

Version2.12.0 (static)

Independent static run, no language model, over the same files as the Cisco scan above. How the two scanners compare across the whole corpus: Two scanners, one corpus.

What this skill does

Cloud Task Planning & Execution for OpenClaw. Makes your agent's work transparent and trackable. Structure all actions into persistent tasks with context notes. Watch progress unfold in real-time via web or mobile — no more \"what are you working on?\" interruptions.

Package: 1 file, 5.9 KB
SKILL.md: 790 words, 11 sections
Code: None. Instructions only.
Requires: env: MCP_API_URL MCP_USER_API_KEY MCP_PROJECT_ID
Homepage: https://taskr.one

SKILL.md covers: Taskr — Observable Task & Memory System · Why Use Taskr? · When to Use Taskr · Important Context · Setup · Authentication & Protocol · Rate Limits · Core Workflow · Quick Reference · Notes as Memory · Task Types for General Use

Findings

MEDIUM Hardcoded External API Endpoint Without Verification Data Exfiltrationllm

The skill hardcodes an external API endpoint (https://taskr.one/api/mcp) that will receive all task data, notes, and potentially sensitive project information. While this appears to be the legitimate Taskr service, there is no mechanism to verify the endpoint's authenticity or warn users about data transmission to third-party servers. Users may unknowingly send sensitive project details, code context, and work patterns to an external service.

SKILL.md

```json
{
  "skills": {
    "entries": {
      "taskr": {
        "env": {
          "MCP_API_URL": "https://taskr.one/api/mcp",
```

Remediation: 1. Add explicit disclosure in the description that this skill transmits data to external servers 2. Include privacy policy link and data handling information 3. Warn users during setup about what data will be transmitted 4. Consider adding opt-in consent for data transmission 5. Document what data is sent to the external API

MEDIUM User API Key Exposure Risk Data Exfiltrationllm

The skill requires users to provide their API key (MCP_USER_API_KEY) through configuration, which will be stored in the gateway config. The instructions direct users to obtain this key from the Taskr web interface but provide no guidance on secure storage, rotation, or scope limitations. If the gateway config is compromised or accidentally shared, the API key could enable unauthorized access to the user's Taskr account and all associated project data.

SKILL.md

2. **Configure via gateway.config.patch:**
   ```json
   {
     "skills": {
       "entries": {
         "taskr": {
           "env": {
             "MCP_API_URL": "https://taskr.one/api/mcp",
             "MCP_PROJECT_ID": "<project-id>",

Remediation: 1. Add security warnings about API key protection 2. Recommend using environment variables instead of config files 3. Provide guidance on key rotation and revocation 4. Document the scope and permissions of the API key 5. Warn against committing config files with keys to version control 6. Consider implementing key validation before storage

LOW Skill does not specify a license Policy Violationstatic

Skill manifest does not include a 'license' field. Specifying a license helps users understand usage terms.

SKILL.md

Remediation: Add 'license' field to SKILL.md frontmatter (e.g., MIT, Apache-2.0)

LOW Missing Critical Metadata Fields Social Engineeringllm

The skill manifest is missing several important metadata fields: 'license' (not specified), 'compatibility' (not specified), and 'allowed-tools' (not specified). While allowed-tools is optional, the absence of license and compatibility information makes it difficult for users to assess legal usage rights and technical requirements. The skill also references a custom 'openclaw' metadata section with environment requirements, but this non-standard format may not be recognized by all agent systems.

SKILL.md

YAML Manifest Details:
- name: taskr
- description: Cloud Task Planning & Execution for OpenClaw...
- license: Not specified
- compatibility: Not specified
- allowed-tools: Not specified
- additional metadata: {'openclaw': {'emoji': '📋', 'requires': {'env': ['MCP_API_URL', 'MCP_USER_API_KEY', 'MCP_PROJECT_ID']}, 'primaryEnv': 'MCP_USER_API_KEY'}}

Remediation: 1. Add explicit license field (e.g., MIT, Apache-2.0, proprietary) 2. Specify compatibility (which agent systems support this skill) 3. Consider adding allowed-tools to document expected agent capabilities 4. Document the 'openclaw' metadata format if it's a custom extension 5. Add version field for skill versioning

LOW Incomplete Setup Instructions Social Engineeringllm

The setup instructions in SKILL.md are truncated, ending abruptly at line 50 with an incomplete JSON configuration block. The instruction shows 'MCP_PROJECT_ID': '<project-id>' but the JSON is not closed, and the MCP_USER_API_KEY configuration line is cut off. This could lead to configuration errors or users being unable to properly set up the skill.

SKILL.md

2. **Configure via gateway.config.patch:**
   ```json
   {
     "skills": {
       "entries": {
         "taskr": {
           "env": {
             "MCP_API_URL": "https://taskr.one/api/mcp",
             "MCP_PROJECT_ID": "<project-id>",
             

(instruction body ends abruptly)

Remediation: 1. Complete the JSON configuration example with proper closing braces 2. Include the full MCP_USER_API_KEY configuration line 3. Add example values for all required fields 4. Provide complete setup verification steps 5. Include troubleshooting guidance for common setup issues

LOW Referenced Files Not Found in Package Social Engineeringllm

The skill references two files ('structured.py' and 'the.py') in its instructions, but these files are not included in the skill package. These appear to be false positives from filename extraction (likely extracted from phrases like 'structured' and 'the' in the markdown text), but their absence could cause confusion if users or agents attempt to locate them. This suggests potential issues with the skill packaging or documentation.

Referenced Files:
Files referenced in instructions: structured.py, the.py

**Referenced File: structured.py** (not found)
**Referenced File: the.py** (not found)

Remediation: 1. Verify if these files should actually be included in the skill package 2. If they are false positives, improve filename extraction logic 3. If they are required, add them to the package 4. Update documentation to clarify which files are included 5. Add a manifest or file listing to document package contents

What is in the package

File	Kind	Size
`SKILL.md`	doc	5.9 KB

External hosts referenced

taskr.one

Hostnames that appear in the skill's files. Referencing a host is not a finding; compare against the findings above and the skill's stated purpose.

Environment variables referenced

MCP_API_URL MCP_PROJECT_ID MCP_USER_API_KEY

Package contents recorded 2026-10-22. The scan above ran against the version current at scan time; the two can differ if the skill has since been updated.

What we checked

Static analyzer. Pattern rules over SKILL.md and bundled files: known-bad commands, exfiltration URLs, secrets, obfuscation.
Llm analyzer. A language model reads the skill and reports intent-level issues the rules cannot express.
Meta analyzer. A second model pass that validates, deduplicates and re-scores the other analyzers' findings.

What we did not check

Runtime behaviour. The skill was not executed; findings come from reading its files.
Anything fetched at install or run time, including remote scripts, package dependencies, and URLs the skill tells the agent to open.
Content the analyzers cannot read: images, binaries, and some non-English text.
Known scanner bypass classes. See the methodology and limitations page.

Sources

Repository: https://clawhub.ai/skills/taskr
Raw scan result: taskr-remote-task-tracking-for-ai-agents-scan.json
Badge for your README: ![skillscan.io](https://skillscan.io/badge/clawhub-ai-taskr.svg)
Request a re-scan

Second scanner: NVIDIA SkillSpector

What this skill does

Findings

What is in the package

External hosts referenced

Environment variables referenced

What we checked

What we did not check

Sources

Related skills