ClawHub
Back to skill

Security audit

Digiforma

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Digiforma API helper, but users should treat its results as sensitive training, invoice, and contact data.

Install only for users who are authorized to access the connected Digiforma account. Avoid broad queries when not needed, and do not expose trainee contact details or invoice information unless the requester has a legitimate need.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill is explicitly designed to retrieve trainee, trainer, and invoice records that include personal and potentially sensitive business data, but it provides no warning or usage constraints around handling PII. In an agent context, this increases the chance of over-broad data retrieval and disclosure to users who may not be authorized to view personal records.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% 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 22)May include surrounding context.

Use curl:

bash
curl -s -X POST https://app.digiforma.com/api/v1/graphql \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $DIGIFORMA_API_KEY" \
  -d '{"query": "YOUR_GRAPHQL_QUERY"}'

Static analysis

No suspicious patterns detected.