ClawHub
Back to skill

Security audit

session-management

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only session-management skill that explains Claude Code resume and naming workflows, with privacy considerations around retained session memory.

Install only if you want help organizing and resuming Claude Code work. Avoid using named sessions or automatic memory for secrets, credentials, or highly sensitive projects unless you are comfortable with prior context being retained and recalled later.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Context Leakage

High
Category
Data Exfiltration
Confidence
75% confidence
Finding

Code or instructions that leak agent conversation context to external services, potentially exposing sensitive user interactions.

Content

Scanner excerpt · SKILL.md (reported line 159)May include surrounding context.

md
Combine session management with other Sanctum skills:

1. **Before starting**: Run `Skill(sanctum:git-workspace-review)` to capture context
2. **Name the session**: `/rename <descriptive-name>`
3. **Work**: Use appropriate skills for the task
4. **Resume if needed**: `claude --resume <name>`

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest trigger list contains generic terms like "session," "resume," and "debugging," plus a broad natural-language condition about organizing long-running work. These phrases overlap with common user intents and do not clearly constrain when this skill should activate versus when other skills should.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill describes automatic memory capture and recall across sessions without a prominent warning that prior session content may be retained and reintroduced into future contexts. This can cause users to unknowingly expose sensitive project details, credentials, or prior conversation content across tasks and repos, especially when combined with resume workflows.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.