Back to skill

Security audit

Handoff Receiver

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed handoff-continuation workflow that reads and updates project handoff files, with no hidden install code or unrelated data access found.

Install this only if you want agents to resume work from project handoff files. Review handoff contents before relying on them, because the skill will treat the active handoff's goal and next steps as the source of work to continue and may update handoff metadata in the repository.

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
Vulnerability Patterns
  • Memory PoisoningPersistent Context Injection, Context Window Stuffing, Memory Manipulation
  • 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 (2)

Memory Manipulation

High
Category
Memory Poisoning
Confidence
80% confidence
Finding

Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.

Content

Scanner excerpt · SKILL.md (reported line 13)May include surrounding context.

md
Use this skill when you are the new skill/agent receiving work from a previous session handoff file.

Goal: continue delivery with minimal drift, no scope expansion, and clear state recovery.

## Step 1: Locate the active handoff and index

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger phrase "resume" is broad and commonly used in normal conversation, so the skill may activate when a user did not intend to invoke handoff continuation behavior. In this skill's context, accidental activation is meaningful because it could cause the agent to load prior-session state, continue old tasks, and update handoff metadata without a clear, explicit user request.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.