Security audit
Security checks for vulnerabilities and agentic risk
This is a disclosed remote image-editing skill that sends images to AgentPMT and stores outputs by default, with no evidence of hidden local execution or deceptive behavior.
Install only if you are comfortable sending image inputs, referenced URLs, and generated outputs to AgentPMT-hosted infrastructure. Avoid sensitive, regulated, or private-link images unless remote processing is approved, and consider disabling storage with store_file=false when persistence is not needed.
The skill prominently describes image editing features but does not clearly warn at the start that user-supplied images, URLs, and outputs are sent to and stored on a remote third-party service. This can lead agents or users to transmit sensitive screenshots, documents, or personal imagery without informed consent, increasing privacy and data-handling risk.
The listed 'Search and activation keywords' include long natural-language task descriptions and generic phrases such as 'image editor', 'blur', 'image base64', and 'image url'. These overlap with ordinary discussion of images and could cause unintended invocation because the file does not clearly bound when the skill should not activate or provide negative examples.
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
- What AgentPMT is: ../what-is-agentpmt (ClawHub: `what-is-agentpmt`, page: https://clawhub.ai/agentpmt/what-is-agentpmt; skills.sh: `npx skills add AgentPMT/agent-skills --skill what-is-agentpmt`)
- AgentPMT account MCP/REST setup: ../agentpmt-account-mcp-rest-api-setup (ClawHub: `agentpmt-account-mcp-rest-api-setup`, page: https://clawhub.ai/agentpmt/agentpmt-account-mcp-rest-api-setup; skills.sh: `npx skills add AgentPMT/agent-skills --skill agentpmt-account-mcp-rest-api-setup`)
- Marketplace product: https://www.agentpmt.com/marketplace/image-editor
- AgentPMT main MCP server: https://api.agentpmt.com/mcp/
- AgentPMT REST invoke endpoint: https://api.agentpmt.com/products/purchase
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
- What AgentPMT is: ../what-is-agentpmt (ClawHub: `what-is-agentpmt`, page: https://clawhub.ai/agentpmt/what-is-agentpmt; skills.sh: `npx skills add AgentPMT/agent-skills --skill what-is-agentpmt`)
- AgentPMT account MCP/REST setup: ../agentpmt-account-mcp-rest-api-setup (ClawHub: `agentpmt-account-mcp-rest-api-setup`, page: https://clawhub.ai/agentpmt/agentpmt-account-mcp-rest-api-setup; skills.sh: `npx skills add AgentPMT/agent-skills --skill agentpmt-account-mcp-rest-api-setup`)
- Marketplace product: https://www.agentpmt.com/marketplace/image-editor
- AgentPMT main MCP server: https://api.agentpmt.com/mcp/
- AgentPMT REST invoke endpoint: https://api.agentpmt.com/products/purchase
The schema allows fetching images from arbitrary public URLs without a clear warning that this causes server-side network access and transmits the supplied URL to the remote service. In practice, this can expose private or sensitive URLs, enable unexpected third-party requests, and increase SSRF-style risk if downstream URL validation is weak.
The schema repeatedly documents store_file behavior with defaults that persist edited outputs to cloud storage, but it does not clearly warn users that image contents may be retained remotely by default. This can cause unintentional storage of sensitive images, creating confidentiality and compliance risk if users expect transient processing.
The manifest description limits the skill to blur, crop, resize, rotate, invert colors, plus examples like compositing logos, watermark/text overlays, placeholder images, and remote image inputs. This schema additionally exposes border, draw, shear, transparent-color removal, info, create, and multi-step orchestration actions, which expand the advertised behavior beyond the manifest's enumerated operation list.
No suspicious patterns detected.