product-changelog

Pass

Audited by Gen Agent Trust Hub on Mar 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the infsh CLI to execute various tasks, including image generation (using models like Flux) and screenshot capture via a browser agent. This relies on the vendor's command-line infrastructure.
  • [EXTERNAL_DOWNLOADS]: The documentation references installing additional skill dependencies via the npx skills add command, targeting the vendor's repository (inference-sh/skills).
  • [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection because it can be directed to use the infsh/agent-browser tool to visit external URLs for screenshots. Ingestion points: External URLs processed by the infsh/agent-browser tool (SKILL.md). Boundary markers: The skill does not provide explicit markers or instructions to the agent to ignore potentially malicious content embedded in the web pages it visits. Capability inventory: The skill can execute shell commands through the CLI, interact with a web browser, and trigger various image processing applications (SKILL.md). Sanitization: There is no evidence of sanitization or content validation for data retrieved from external URLs before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 17, 2026, 11:51 AM