ClawHub
Back to skill

Security audit

Post-doc Fellowship Matcher

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple local fellowship-matching helper, but its matching logic is incomplete and should not be relied on for final eligibility decisions.

Safe to install from a security perspective, but treat results as a rough starting point. Verify fellowship eligibility, fields, deadlines, and nationality rules on official program websites, especially because the included script does not actually filter by research field.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The skill promises filtering against nationality, years since PhD, and research field from a curated database, but the finding indicates it does not actually enforce research-field matching and instead relies on a hardcoded list. This can mislead users into trusting eligibility results that are incomplete or stale, causing incorrect recommendations and potential privacy or decision-making harm in an academic funding context.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The manifest says the skill filters and matches opportunities based on applicant nationality, years since PhD, and research field. However, find_matches only checks nationality and years post-PhD, and the field parameter is never used, so the actual matching behavior is narrower than described.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
2% confidence
Finding

This code only prints fellowship match information in English and does not contain any explicit language or locale enforcement policy. The provided policy rule targets natural-language violations such as forcing a specific language without opt-in, which is not clearly present here.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.