dogfood

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes and interprets data from external, untrusted web applications.
  • Ingestion points: Content from {TARGET_URL} is ingested into the agent's context through agent-browser snapshot and agent-browser screenshot commands in SKILL.md.
  • Boundary markers: There are no explicit delimiters or specific instructions to the agent to ignore or isolate instructions that might be embedded in the HTML or DOM of the target site.
  • Capability inventory: The skill utilizes tool capabilities including directory creation (mkdir), file copying (cp), and full browser interaction (clicks, form filling, recording).
  • Sanitization: The skill does not perform any validation or sanitization of the external content retrieved from the web pages before processing it.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 06:39 AM