speckit-proc

Warn

Audited by Snyk on May 7, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 1.00). The skill clearly ingests untrusted user content: stages/01-preflight/CONTEXT.md instructs fetching issue title/body/labels/comments and identifying referenced URLs via gh issue view, and stages/02-specify/CONTEXT.md instructs the worker to "read the issue references, fetch any URLs," meaning arbitrary public issue text and linked web pages are read and used to drive worker actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 7, 2026, 03:31 PM
Issues
1