ClawHub
Back to skill

Security audit

Fact Check

Security checks for vulnerabilities and agentic risk

Overview

This fact-checking skill is a plain Markdown workflow that encourages verification with local and network tools, with no hidden code, persistence, or destructive behavior found.

Install only if you are comfortable with a fact-checking workflow that may run local inspection commands and make outbound requests to package registries, GitHub, documentation sites, or APIs. Avoid using it to contact sensitive internal endpoints or authenticated APIs unless you explicitly intend that verification and understand what request metadata or response data may be exposed.

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
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The activation condition is broad because it triggers not only on explicit user requests to fact-check, but also whenever output contains generic technical indicators like version numbers, API references, dates, or model names. This can cause unnecessary invocation of the skill and may lead the agent to perform verification actions, including network or shell-based checks, in situations where the user did not ask for them.

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 108)May include surrounding context.

md
- [ ] Don't trust your memory for version numbers, API shapes, or dates
- [ ] Don't assume an API field name — always verify from real output
- [ ] Don't report "I fixed it" without verifying CI passes (`gh pr checks`)
- [ ] Don't report "PR has reviews" without checking (`gh pr view`)
- [ ] Don't cite documentation without confirming the URL exists
- [ ] Don't use old StackOverflow answers as current truth — platforms change
- [ ] Don't claim "push succeeded" means "task complete"

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 112)May include surrounding context.

md
- [ ] Don't trust your memory for version numbers, API shapes, or dates
- [ ] Don't assume an API field name — always verify from real output
- [ ] Don't report "I fixed it" without verifying CI passes (`gh pr checks`)
- [ ] Don't report "PR has reviews" without checking (`gh pr view`)
- [ ] Don't cite documentation without confirming the URL exists
- [ ] Don't use old StackOverflow answers as current truth — platforms change
- [ ] Don't claim "push succeeded" means "task complete"

External Transmission

Medium
Category
Data Exfiltration
Confidence
88% confidence
Finding

This instruction explicitly recommends making real outbound API calls to verify field names. In a skill context, that can transmit user-provided or model-generated URLs and request metadata to external services, creating SSRF, data egress, or untrusted-network interaction risk if used on attacker-controlled endpoints.

Content

Scanner excerpt · SKILL.md (reported line 129)May include surrounding context.

Never guess API response field names. Always run the API and read the actual response:

bash
# Real API call to verify field names
curl -s "https://api.example.com/endpoint" | jq '.[0] | keys'

Pattern 3: False Success Reporting

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 172)May include surrounding context.

md
|---------------|-------------------|------------|
| `https://auth.openai.com/activate` | Follows common OAuth patterns | `https://auth.openai.com/codex/device` |
| `https://docs.clawhub.ai` | Standard docs subdomain | Does not exist (returns 404) |
| `https://api.example.com/v2/schema` | Common API convention | Endpoint may not exist |

**Prevention:**
- **Never guess URLs.** If you can't see the full output, ask the user to expand it.

Static analysis

No suspicious patterns detected.