product-price-monitor

Pass

Audited by Gen Agent Trust Hub on Aug 10, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes data from external, untrusted URLs through browser tools, which creates an attack surface for indirect prompt injection if the source content contains malicious instructions.
  • Ingestion points: The web_extract and browser_navigate tools are used to fetch live results from user-provided source URLs (described in Steps 3 and 4 of SKILL.md).
  • Boundary markers: Absent; there are no specific instructions to the agent to ignore embedded commands within the fetched data.
  • Capability inventory: The skill has access to the cronjob tool for persistence, file system write access to ~/.hermes/ for state management, and network operations via browser tools.
  • Sanitization: Absent; the skill relies on the agent to normalize and extract price data from raw page content without explicit sanitization steps.
  • [COMMAND_EXECUTION]: The skill establishes a persistence mechanism by instructing the agent to create recurring background tasks using the cronjob tool to monitor prices periodically.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 10, 2026, 07:40 AM
Security Audit — agent-trust-hub — product-price-monitor