skills/buildinternet/releases/local-ingest/Snyk

local-ingest

Warn

Audited by Snyk on Jul 30, 2026

Risk Level: MEDIUM

Full Analysis

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

Third-party content exposure detected (low risk: 0.10). In SKILL.md Step 4 (Fetch + extract), the local Claude Code agent fetches outsider-authored changelog/index/detail pages provided by the operator (URLs from Step 1/3, including sitemap/index HTML), then ingests that free text into the LLM to extract records.

Issues (1)

W011

MEDIUM

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

Audit Metadata

Risk Level

MEDIUM

Analyzed

Jul 30, 2026, 11:54 AM

Issues

1

Security Audit — snyk — local-ingest