ClawHub
Back to skill

Security audit

handoff

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed project handoff helper that writes local notes and a small project-memory pointer so future sessions can resume work.

Install this if you want local handoff notes and project-memory pointers. Be aware that the generated handoff may contain unfinished reasoning, file paths, commands, branch state, and test failures, so review whether .claude/handoffs should be git-ignored or committed and remove stale memory pointers when the work is done.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest description includes many broad natural-language trigger phrases like 'save context', 'preserve context', and 'before we lose context', which increases the chance the skill is invoked when the user did not explicitly intend to run it. Because this skill writes files and memory entries, unintended activation can cause unexpected persistence of session content or disclosure of work state into project artifacts.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 17)May include surrounding context.

md
- The user signals they're about to compact, switch machines, or hand the work to another teammate / another Claude session.
- You notice the conversation has accumulated significant state (many files touched, several decisions made) and the user explicitly asks to checkpoint.

Do **not** auto-trigger when the user just says "let's stop here" without asking for continuity. Wait for an explicit hand-off cue.

## Output: two artifacts

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 152)May include surrounding context.

md
## Anti-patterns

- Writing the hand-off without checking `git status` — drift between conversation memory and actual repo state.
- Vague "next steps" like "continue the work" — write concrete actions tied to specific files.
- Recording every micro-decision — keep **Decisions** to choices that would be re-litigated otherwise.
- Dumping the entire conversation transcript — hand-off is a synthesis, not a log.

Static analysis

No suspicious patterns detected.