Security audit
Security checks for vulnerabilities and agentic risk
This is a disclosed SlideSpeak API helper, but it sends chosen text or files to SlideSpeak and can configure webhooks, so users should be careful with sensitive content and account credentials.
Install only if you intend to use SlideSpeak as an external service. Treat SLIDESPEAK_API_KEY like a password, expect prompts and uploaded documents to leave the local environment, avoid confidential or regulated files unless approved, watch for credit or billing impact, and use webhook URLs only when you control and trust the destination.
Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
---
### DELETE /webhook/unsubscribe
Remove a webhook subscription.
The script performs outbound network requests to the SlideSpeak API and arbitrary URLs supplied for webhook subscription, but the finding indicates this capability is not covered by declared permissions. Undeclared network access is dangerous in agent environments because it can transmit user data or metadata off-platform without clear authorization boundaries.
The script performs outbound network requests to the SlideSpeak API and arbitrary URLs supplied for webhook subscription, but the finding indicates this capability is not covered by declared permissions. Undeclared network access is dangerous in agent environments because it can transmit user data or metadata off-platform without clear authorization boundaries.
The skill instructs users to upload documents and generate presentations through the SlideSpeak API, but it does not clearly warn that document contents and prompts are transmitted to an external third-party service. This creates a real data-handling risk because users may provide confidential files or sensitive business content without informed consent, leading to unintended disclosure outside the local agent environment.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
# SlideSpeak API Reference
Base URL: `https://api.slidespeak.co/api/v1`
All requests require the `X-API-Key` header with your API key.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
# SlideSpeak API Reference
Base URL: `https://api.slidespeak.co/api/v1`
All requests require the `X-API-Key` header with your API key.
The API reference documents document upload and webhook subscription flows that transmit user-provided files and metadata to an external third-party service, but it provides no warning about privacy, data handling, or consent requirements. In an agent skill, this omission can cause sensitive user documents or internal callback URLs to be sent off-platform without the user clearly understanding that external processing will occur.
The upload command reads a local file and transmits its contents to a remote API without any in-script warning, consent checkpoint, or data-classification guard. In an agent setting, this can cause accidental exfiltration of sensitive local documents when users may not realize the file leaves the local environment.
Webhook subscribe/unsubscribe functionality extends the skill from presentation management into persistent outbound-callback configuration. That creates a data egress and integration surface that is broader than the stated purpose, and could be abused to send task events or links to attacker-controlled endpoints.
The skill documents the need for a SlideSpeak API key but does not warn that using the skill grants access to a third-party account and may incur usage, billing, or data-access consequences. While this is less severe than direct secret exposure, the missing warning can mislead operators about the trust boundary and the implications of providing credentials to enable external API actions.
The slide editing section documents the REMOVE edit type as deleting a slide, but it does not include a caution about data loss or irreversibility. For markdown files, destructive behaviors that affect user data should be accompanied by a clear warning.
No suspicious patterns detected.