harness-eval

Warn

Audited by Snyk on Aug 5, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (medium risk: 0.30). Outsider-authored free text from the target repo is ingested at runtime because the skill reads repo files specified by discovery (including referenced T0/T1/T2 markdown) into inventory_extract.py, writes extracted content into claims.md/surfaces.md, and then the Track B/C LLM judges score that text via <RUN_DIR>/claims.md and <RUN_DIR>/surfaces.md.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 5, 2026, 07:53 PM
Issues
1
Security Audit — snyk — harness-eval