ClawHub
Back to skill

Security audit

NMI Literature Explorer

Security checks for vulnerabilities and agentic risk

Overview

The skill provides bounded literature searches with clearly disclosed API use and proportionate access.

Optional API searches share your query with Springer Nature and use your API quota. Configure SN_API_KEY through the process environment and keep key-bearing URLs out of logs and chat. The official archive remains available without a key.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (4)

Tainted flow: 'request' from os.environ.get (line 161, 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/springer_nature_search.py (reported line 169)May include surrounding context.

python
},
    )
    try:
        with urlopen(request, timeout=30) as response:
            payload = json.load(response)
    except HTTPError as error:
        if error.code == 401:

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: env, network.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 40)May include surrounding context.

md
## Optional metadata helper

The Python 3.10+ script at scripts/springer_nature_search.py makes one request to the Springer Nature Meta API and prints metadata only. Use it only when an API key is configured in the process environment as SN_API_KEY. Never ask the user to paste a secret into chat, put a key in a file, print it, or include a key-bearing request URL in the answer.

The script searches a quoted phrase and/or year within the publication constraint Nature Machine Intelligence. It returns one bounded page of results; it does not crawl, paginate, download full text, save a corpus, or replace archive verification. The user's query is sent to Springer Nature. If the script is unavailable, the key is absent, or the API does not return useful results, continue with the official NMI archive.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · scripts/springer_nature_search.py (reported line 18)May include surrounding context.

python
from urllib.request import Request, urlopen


API_URL = "https://api.springernature.com/meta/v2/json"
JOURNAL_TITLE = "Nature Machine Intelligence"
FIELDS = (
    "title",