ClawHub
Back to skill

Security audit

Session Log

Security checks for vulnerabilities and agentic risk

Overview

This skill locally creates and maintains simple session summary files, with no evidence of hidden network access, credential use, or destructive behavior.

Install only if you want persistent local conversation summaries. Keep logs in a known workspace sessions folder, do not include secrets or sensitive personal data, and define how long logs should be retained or deleted.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (5)

Tp4

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding

The code only implements initial session file creation. It accepts an agent name and output directory, creates the directory if needed, and writes a timestamped markdown file with a basic header. The declared description claims broader behavior: automatic execution on every session start including /new resets, appending topic summaries during conversation, and supporting persistent audit trails and daily summaries. Those capabilities are not present in this code chunk. While the filename and agent handling are consistent with part of the description, the actual behavior is materially narrower than the declared purpose.

Content

No source excerpt is available for this finding.

Missing User Warnings

High
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill promotes persistent conversation logging across /new resets and multi-agent daily aggregation without any clear privacy notice, consent boundary, retention policy, or guidance on excluding secrets and sensitive content. This is dangerous because users and operators may assume resets clear context, while the skill silently preserves summaries that can expose confidential prompts, personal data, credentials, or internal project details to later readers and cron jobs.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

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.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The manifest description says to use the skill for 'session continuity, conversation audit trails, or multi-agent daily summaries' and that it 'Works for main, writer, coding, or any agent.' This is broad and does not define clear trigger phrases, scope boundaries, or exclusion conditions, increasing the risk of unintended invocation in ordinary workflows.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The script hard-codes CST (UTC+8) and uses it for session timestamps, which imposes a locale-specific behavior on all users. There is no option to choose a timezone and no inline justification that this is a region-specific tool, so it may violate language/locale policy expectations.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.