price-monitor

Warn

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: MEDIUMDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [DYNAMIC_EXECUTION]: The skill generates and executes Node.js code at runtime using the node -e flag in the periodic monitoring step. The generated script interpolates shell variables ($HISTORY) and placeholders ({CURRENT_PRICE}, {URL}) directly into the JavaScript source string without sanitization. This creates a vulnerability where a maliciously crafted URL or price value could break out of the string literal and execute arbitrary JavaScript or shell commands.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external, untrusted websites through the COMPOSIO_SEARCH_FETCH_URL_CONTENT and BROWSER_TOOL_CREATE_TASK tools.
  • Ingestion points: Product and SaaS pricing pages specified by the user or discovered during search (SKILL.md).
  • Boundary markers: The instructions provided to the browser tool do not include delimiters or warnings to ignore instructions embedded within the target website's content.
  • Capability inventory: The skill has the ability to write to the local file system (~/Desktop/price-monitor/), execute local shell commands, and run Node.js scripts.
  • Sanitization: There is no evidence of sanitization or validation of the data extracted from the web pages before it is used in downstream logic or file writes.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Sep 17, 2026, 02:14 PM