ClawHub
Back to skill

Security audit

Literature Review

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed literature-search helper that sends user queries to academic APIs and does not show hidden, destructive, or persistent behavior.

Install only if you are comfortable sending your literature search terms to Semantic Scholar, OpenAlex, Crossref, and PubMed. Avoid setting USER_EMAIL or API-key environment variables unless you want those identifiers used for the corresponding services.

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 (7)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding

The skill explicitly describes use of environment variables and multiple external networked APIs, but it does not declare any tool scope such as permissions or allowed-tools. That creates an authorization and transparency gap: an agent may invoke network access and read env-backed secrets without an explicit contract, increasing the risk of unintended data exposure or misuse in environments that rely on manifest-level restrictions.

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 83)May include surrounding context.

md
- **Citations**: Always cross-reference the DOI or PMID for accuracy in bibliography.
- **Filtering**: Focus on papers with higher `citationCount` or recent years for a more modern review.
- **PubMed for Medicine**: Use `--source pm` for the most reliable biomedical literature.
- **Deduplication**: Multi-source searches automatically remove duplicates; use single sources if you need raw counts.

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/lit_search.py (reported line 10)May include surrounding context.

python
import time
import xml.etree.ElementTree as ET

S2_BASE_URL = "https://api.semanticscholar.org/graph/v1"
OA_BASE_URL = "https://api.openalex.org"
CR_BASE_URL = "https://api.crossref.org/works"
PM_BASE_URL = "https://eutils.ncbi.nlm.nih.gov/entrez/eutils"

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/lit_search.py (reported line 12)May include surrounding context.

python
S2_BASE_URL = "https://api.semanticscholar.org/graph/v1"
OA_BASE_URL = "https://api.openalex.org"
CR_BASE_URL = "https://api.crossref.org/works"
PM_BASE_URL = "https://eutils.ncbi.nlm.nih.gov/entrez/eutils"

# Timeout for all requests (seconds)

Tainted flow: 'fetch_params' from requests.get (line 182, network input) → requests.get (network output)

Medium
Category
Data Flow
Confidence
65% confidence
Finding

Data from a source is assigned to a variable that is later passed to a sink, creating a variable-mediated taint flow.

Content

Scanner excerpt · scripts/lit_search.py (reported line 188)May include surrounding context.

python
"retmode": "xml",
            "rettype": "abstract"
        }
        fetch_res = requests.get(fetch_url, params=fetch_params, timeout=REQUEST_TIMEOUT)
        if fetch_res.status_code != 200:
            return {"error": f"efetch HTTP {fetch_res.status_code}", "data": []}

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The package description is written only in Chinese ("文献综述辅助技能"), which may indicate a language-specific user experience without documenting user choice or opt-in. The policy requires avoiding forced language or locale constraints unless they are explicitly offered as a choice or clearly justified.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

User-provided search terms and a configured email address are transmitted to third-party academic APIs, which can expose potentially sensitive research interests or identifying contact metadata to external services. In this skill context, external lookup is core functionality, so the behavior is expected, but the code provides no explicit consent, minimization, or warning mechanism around that disclosure.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.