product-agent

Pass

Audited by Gen Agent Trust Hub on Jun 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a vulnerability surface for indirect prompt injection through its research workflow.
  • Ingestion points: The skill utilizes the WebFetch tool to retrieve content from external websites and competitor pages during its research process (SKILL.md).
  • Boundary markers: The instructions do not define clear delimiters or specific instructions for the agent to ignore or isolate potential commands embedded within the fetched external web content.
  • Capability inventory: The skill is permitted to use the Write tool (SKILL.md), providing a mechanism where successfully injected instructions could potentially influence the agent to write unauthorized or malicious content to the filesystem.
  • Sanitization: There is no evidence of content validation, escaping, or filtering for the external data before it is processed by the agent's logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 18, 2026, 05:18 PM
Security Audit — agent-trust-hub — product-agent