ClawHub
Back to skill

Security audit

Grant Funding Scout

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed demo tool that uses mock grant-funding data and only performs local report generation, with no evidence of hidden network access, persistence, credential use, or destructive behavior.

Install only if you want a demo or template for grant-funding analysis. Do not rely on its outputs for real NIH strategy without replacing the mock data and heuristic matching with authoritative funding sources, and keep any --output path inside your workspace.

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 Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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
Findings (3)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding

The skill describes file-writing capability via the --output parameter and its risk table, but it does not declare any explicit tool scope such as permissions or allowed-tools. This creates a policy/permission mismatch where an agent may be able to write files without clear authorization boundaries, increasing the risk of unintended or unsafe file creation if the skill is executed in a broader environment.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill advertises NIH funding trend analysis, but the implementation relies entirely on hardcoded mock categories and fabricated trend values. This can mislead users into treating synthetic output as evidence-based funding intelligence, causing bad research planning or grant-targeting decisions in a domain where accuracy and provenance matter.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The report format conveys authoritative recommendations, but the matching logic is only substring heuristics for opportunities and institute suggestions. This creates a deceptive level of confidence around simplistic inferences, which may steer users toward inappropriate research priorities or institute targets.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.