dogfood

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill has a vulnerability surface for indirect prompt injection as it processes untrusted data from external web applications.
  • Ingestion points: Data enters the agent context via camofox snapshot, camofox errors, and camofox console in SKILL.md.
  • Boundary markers: No delimiters are present to separate system instructions from retrieved website content.
  • Capability inventory: The agent can click, type, and navigate within a browser using the camofox toolset.
  • Sanitization: No sanitization is performed on the ingested content before it is processed.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 04:00 AM