skills/maroffo/claude-forge/autoresearch-prompt/Snyk

autoresearch-prompt

Warn

Audited by Snyk on Jul 15, 2026

Risk Level: MEDIUM

Full Analysis

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

Third-party content exposure detected (high risk: 0.95). Outsider-authored free text from eval_set.jsonl (e.g., newsletter content/subject/from fields) is loaded at runtime and rendered into the LLM user message via evaluator.load_eval_set() → prompt_loader.load_and_render() → call_llm().

Issues (1)

W011

MEDIUM

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

Audit Metadata

Risk Level

MEDIUM

Analyzed

Jul 15, 2026, 01:44 AM

Issues

1

Security Audit — snyk — autoresearch-prompt