ClawHub
Back to skill

Security audit

Agently Playbook

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only Agently planning skill with broad routing guidance, but it does not request sensitive access, execute code, persist changes, or hide behavior.

Install this only if you want generic model-app planning requests to be steered toward Agently-native architecture choices. If you prefer framework-neutral guidance unless Agently is explicitly requested, this skill's broad activation wording may be too aggressive.

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 (5)

Vague Triggers

High
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger description is extremely broad and matches common requests like building assistants, tools, automations, or workflows even when the user does not mention the framework. In a skill-routing system, this can cause over-selection of this skill, shadowing more specific skills and steering user requests into an unintended execution path, which is a real security and safety boundary issue when skill choice affects subsequent behavior.

Content

No source excerpt is available for this finding.

Vague Triggers

High
Category
Not specified by scanner
Confidence
96% confidence
Finding

The example phrases like "build an assistant" or "design an internal tool" are generic enough to collide with a large share of normal user requests. Because the skill explicitly instructs routing even without framework-specific terms, the context makes this more dangerous: it increases the chance of inappropriate invocation and can bias downstream design, implementation, or tool-selection decisions.

Content

No source excerpt is available for this finding.

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 50)May include surrounding context.

md
- `references/capability-map.md`

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 51)May include surrounding context.

md
- `references/project-framework.md`

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The capability map explicitly routes broad, generic requests such as 'help me kick off a model-powered internal tool' or 'build a requirements assistant' into this skill before the user's intent is tightly scoped. That increases the chance this skill is invoked for ambiguous requests outside its safest operating boundary, which can cause over-broad authority, incorrect routing, or premature project generation decisions that may bypass more specialized controls.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.