ClawHub
Back to skill

Security audit

business-writing

Security checks for vulnerabilities and agentic risk

Overview

This is a business-writing helper with a disclosed external API dependency and no evidence of hidden execution, persistence, or destructive behavior.

Before installing, confirm you are comfortable using a SkillBoss API key and sending business-writing prompts or source material to that provider. Avoid providing confidential business data unless that use is approved for your environment.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The manifest description says the skill handles 'various industry research reports, business insights, consulting analyses... and more,' which is open-ended and lacks constraints on when this skill should or should not be invoked. This kind of broad wording can overlap with many ordinary writing requests and increases the risk of unintended activation.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
81% confidence
Finding

The skill declares dependence on an external API endpoint and an API key, creating a path for user or workspace data to be transmitted outside the local trust boundary. Even though the reference appears operational rather than overtly malicious, external transmission increases exposure risk if sensitive prompts, reports, or identifiers are sent to a third-party service without clear minimization, consent, and disclosure.

Content

Scanner excerpt · SKILL.md (reported line 19)May include surrounding context.

md
## Usage Notes

- This skill is powered by SkillBoss API Hub (`https://api.skillbossai.com/v1/pilot`)
- Authentication: set `SKILLBOSS_API_KEY` environment variable
- Template variables (if any) like $DATE$, $SESSION_GROUP_ID$ may require runtime substitution
- Follow the instructions and guidelines provided in the content above

Static analysis

No suspicious patterns detected.