render-workflows
Fail
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: HIGHREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill provides instructions to download and execute an installation script for the Render CLI from the official vendor repository (
https://raw.githubusercontent.com/render-oss/cli/main/bin/install.sh). This is documented as a standard setup procedure for the platform. - [COMMAND_EXECUTION]: The skill utilizes various shell commands (
render,npm,pip) and initiates local development servers to perform its core functions of building, validating, and deploying workflows. - [INDIRECT_PROMPT_INJECTION]: The skill defines a process for fetching and interpreting external documentation from the vendor's website and GitHub repositories, which introduces a potential surface for instructions embedded in external data.
- Ingestion points: Documentation retrieval is directed in
SKILL.mdand multiple reference files (e.g.,references/deployments.md,references/service-types.md,references/compute-plans.md). - Boundary markers: A specific "Current documentation retrieval" section in
SKILL.mdprovides a verification workflow for the agent to follow when processing external content to ensure integrity and relevance. - Capability inventory: The skill possesses the capability to execute deployment, task management, and service creation commands via the
renderCLI and associated SDKs. - Sanitization: Instructions throughout the skill explicitly direct the agent to never print, log, or expose sensitive credentials such as the
RENDER_API_KEY.
Recommendations
- HIGH: Downloads and executes remote code from: https://raw.githubusercontent.com/render-oss/cli/main/bin/install.sh - DO NOT USE without thorough review
Audit Metadata