Back to skill

Security audit

contentforge-api

Security checks for vulnerabilities and agentic risk

Overview

This skill is a normal external content-generation integration, but it can send your email and writing inputs to a third-party service with weak consent and scoping instructions.

Review this before installing if you handle private drafts, customer data, business plans, or regulated information. Only use it when you intentionally want ContentForge involved, confirm what will be sent, avoid secrets or sensitive content, and store any API key in an approved secret store rather than prompts, files, or logs.

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
Findings (1)

other

Warning
Location
SKILL.md:17
Finding

External Disclosure of Personal and Potentially Confidential Content Without Explicit Consent Controls

Content
View full analysis
Remediation
View remediation
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 (4)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The signup flow instructs the agent to collect the user's email and transmit it to an external service, but it does not require informing the user of that transfer. This creates a privacy and consent issue because personally identifiable information is being sent off-platform without an explicit warning or confirmation step.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
96% confidence
Finding

This line performs an outbound request containing the user's email address to a third-party endpoint. The transmission itself is expected functionality, but in the absence of disclosure and consent safeguards in the skill, it represents a real privacy-sensitive data exfiltration path.

Content

Scanner excerpt · SKILL.md (reported line 23)May include surrounding context.

Step 2: Sign Up via API

bash
curl -X POST https://contentforge.vosscg.com/v1/keys \
  -H "Content-Type: application/json" \
  -d '{"email":"user@example.com"}'

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The examples show sending user-provided content inputs directly to the external generation API without warning that prompts, product details, marketing plans, or other text may leave the local environment. In a writing skill, those inputs may easily contain confidential business data, unpublished content, or personal information, making silent transmission risky.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The activation guidance is extremely broad, covering essentially any writing or text-generation request. That can cause the skill to trigger in many ordinary conversations without clearly signaling to the user that their prompts may be routed to a third-party API, increasing the chance of unintended external disclosure of sensitive or proprietary text.

Content

No source excerpt is available for this finding.