ClawHub
Back to skill

Security audit

Agent Harness Engineering

Security checks for vulnerabilities and agentic risk

Overview

This skill is a repo-scaffolding helper that makes disclosed, purpose-aligned documentation and validation changes without evidence of hidden execution, exfiltration, or destructive behavior.

Install this only if you want an agent to modify repository documentation and validation structure. Run the bootstrap in dry-run mode first on important repositories, review AGENTS.md and generated docs before committing, and use the optional garbage-collection flow as reporting rather than automatic deletion.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (3)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
96% confidence
Finding

The skill explicitly instructs the agent to inspect repositories, run a bootstrap script, update files, create symlinks, and wire validation into CI, which implies file read/write and shell execution. Because no permissions or allowed-tools scope is declared, the skill leaves powerful capabilities unconstrained, increasing the chance of unintended repo modification or command execution in the wrong context.

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 159)May include surrounding context.

md
- do not rewrite a mature doc system unless the user asks
- do not duplicate the same guidance in `AGENTS.md` and `docs/agent/*`
- do not add stack-specific CI assumptions without checking the repo
- do not enable automatic destructive cleanup; GC should surface candidates, not delete code blindly

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill is configured with a broad default prompt and allow_implicit_invocation set to true, which can cause the skill to activate in situations beyond the user's explicit intent. That increases the chance of unreviewed repository-wide modifications or policy scaffolding being applied automatically, especially because this skill affects project structure, documentation, and guardrails across the repo.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.