rubber-duck
Warn
Audited by Snyk on Jun 19, 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). Outsider free text is ingested into the critic LLM context via the host agent running the chosen outsider CLI with
{prompt}populated from the user’s work (plan/diff/tests) and the rubric file; this is not authored by the operating user and is passed as readable prompt content to the critic model through thesubprocess_command/discoverpath inSKILL.md(host executes the command).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata