ClawHub
Back to skill

Security audit

discovery-call-prep

Security checks for vulnerabilities and agentic risk

Overview

The bundled code performs limited local checks, although it does not generate the discovery brief promised in the description.

Expect a field-checking report rather than a generated brief; the supplied template also needs correction to match the script. Choose an output folder where replacing discovery-brief.md is acceptable. The optional Windows app is unnecessary for this workflow and requires a separate security decision; the supplied checksum alone does not establish its safety.

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)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The primary implemented function is a completeness and length checker for already-authored fields. It does not transform prospect information and call notes into the promised discovery brief. Reading local input and writing a report are ordinary supporting operations, and there is no evidence of unrelated access or exfiltration; the mismatch is between the declared generation capability and the actual validation-only behavior.

Content

No source excerpt is available for this finding.

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

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.

The script produces a field-validation report rather than the promised discovery brief.

Medium
Category
Excessive Agency
Confidence
98% confidence
Finding

The manifest promises to turn public records and call notes into a discovery brief containing questions, risks, and a next step. Instead, the script expects prewritten brief fields and outputs only their presence and character counts, plus fixed guardrail text; it neither derives the promised content nor includes the supplied field contents in discovery-brief.md.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.