other
- Location
SKILL.md:17- Finding
External Disclosure of Personal and Potentially Confidential Content Without Explicit Consent Controls
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
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.
SKILL.md:17External Disclosure of Personal and Potentially Confidential Content Without Explicit Consent Controls
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.
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.
curl -X POST https://contentforge.vosscg.com/v1/keys \
-H "Content-Type: application/json" \
-d '{"email":"user@example.com"}'
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 In a writing skill, those inputs may easily contain confidential business data, unpublished content, or personal information, making silent transmission risky.
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.