competitor-teardown

Pass

Audited by Gen Agent Trust Hub on Mar 7, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill documentation instructs the user to install dependencies from the inference-sh organization using the npx package runner.
  • [COMMAND_EXECUTION]: The skill uses the infsh CLI to execute various sub-applications, including a Python executor for generating charts with matplotlib and an agent-controlled browser for capturing screenshots.
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection because it is designed to ingest and analyze data from untrusted external sources.
  • Ingestion points: Data is ingested from external URLs through web extraction tools, search assistants, and browser automation.
  • Boundary markers: The skill does not define specific delimiters or instructions to ignore commands that may be embedded within the retrieved website content.
  • Capability inventory: The agent has permissions to use the infsh CLI, which includes capabilities for searching the web, browsing sites, and executing Python code.
  • Sanitization: The skill does not implement sanitization or filtering of the scraped content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 7, 2026, 12:07 PM