ClawHub
Back to skill

Security audit

pcap-analysis

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward PCAP analysis helper, with only low-risk local file reading and an optional CSV-writing example to watch for.

Install only if you are comfortable using a Python/Scapy helper on PCAP files. Treat the security detections as best-effort heuristics, and be careful with the sample CSV code because it rewrites network_stats.csv in the current directory.

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)

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The module-level documentation makes strong trust-building claims such as 'tested, correct implementations' and 'strict, calibrated thresholds,' but those claims are not reliably supported by the code and can mislead downstream agents or users into over-trusting detection results. In a security-analysis skill, inaccurate assurances about detection logic can cause false negatives or false positives to be accepted without scrutiny, degrading incident triage and defensive decision-making.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

The manifest describes analysis guidance and computation of network statistics, which is primarily read/compute behavior over PCAP data. The 'Writing Results to CSV' section adds filesystem modification behavior by rewriting network_stats.csv, which is not reflected in the manifest's stated scope.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

This markdown file includes example code that opens an existing CSV file and then rewrites it in place. Because markdown files are in scope for SQP-2, the description should disclose file-modifying behavior that could affect user data, but no warning is given near this example.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.