Skills
skills/flpbalada/fb-skills/dogfood/Gen Agent Trust Hub

dogfood

Pass

Audited by Gen Agent Trust Hub on May 4, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill defines a standard QA testing workflow and uses authorized tools for browser automation.
  • [INDIRECT_PROMPT_INJECTION]: The skill interacts with external web content, which presents a surface for indirect prompt injection.
  • Ingestion points: SKILL.md uses agent-browser to read data from the TARGET_URL.
  • Boundary markers: None. No specific delimiters are used to wrap ingested page content.
  • Capability inventory: The agent has access to agent-browser and Bash file system commands.
  • Sanitization: None. External content is processed directly to identify application issues.
Audit Metadata
Risk Level
SAFE
Analyzed
May 4, 2026, 08:21 AM