dogfood

Warn

Audited by Snyk on Jun 29, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.75). In scripts/dogfood.sh the explore subcommand composes a web-app exploratory workflow that reads references/exploratory-issue-taxonomy.md (bundled) and then uses agent-browser to open a runtime-supplied --url/detected site; the resulting page content, errors, and console text from that outsider web content can be ingested into the agent’s LLM context via the browser session.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 29, 2026, 02:41 AM
Issues
1
Security Audit — snyk — dogfood