The Agent Skills Directory

Prompt Injection (LOW): Detected a potential surface for Indirect Prompt Injection through external data ingestion. 1. Ingestion points: The agent reads service names and project lists via RENDER_LIST_SERVICES and RENDER_LIST_PROJECTS. 2. Boundary markers: Absent; there are no instructions to the agent to disregard instructions embedded in resource names. 3. Capability inventory: The agent can perform write actions such as RENDER_TRIGGER_DEPLOY. 4. Sanitization: Absent; no validation or escaping of the service names is mentioned.
No Code (SAFE): The skill consists entirely of markdown instructions and configuration metadata. No executable scripts, binaries, or package dependency files were found in the analyzed skill.

render-automation