ClawHub
Back to skill

Security audit

Agent Design Review

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only skill for reviewing LLM agent designs, with no bundled code or hidden authority requests.

Installers should expect this skill to shape responses for agent architecture reviews. It is benign as packaged, though users may want narrower invocation wording if they have many adjacent agent-design skills installed.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The description activates on phrases like 'review an agent architecture', 'debug an agent that loops or goes off-task', or 'harden an agent before launch', which are broad enough to match many general-purpose discussions about agents. The file does not provide explicit exclusion conditions or negative examples to clarify when this skill should not be invoked instead of other review or debugging skills.

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 49)May include surrounding context.

md
| Tool use | overlapping tools confuse selection | Med | fewer, sharply-described tools; allowlist |
| Context | full history re-sent each step → cost + drift | High | summarise/scope memory per step |
| Failure handling | one tool error aborts the run | Med | retry/backoff + graceful degradation |
| Safety | acts without confirmation on writes | High | human/confirm gate on side-effecting actions |

**3. Reliability checklist** — termination guarantee (it always stops), error recovery, idempotency of
side-effecting actions, and determinism where it matters.

Static analysis

No suspicious patterns detected.