skills/amit-t/skills/session-to-skill-extractor/Snyk

session-to-skill-extractor

Warn

Audited by Snyk on Sep 18, 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). The agent skill extracts procedures from completed agent session transcripts across various hosts (Claude Code, Codex, Devin, Copilot, or generic user-supplied files), which can contain outsider-authored user turns and prompt injection content.

Issues (1)

W011

MEDIUM

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

Audit Metadata

Risk Level

MEDIUM

Analyzed

Sep 18, 2026, 07:54 AM

Issues

1

Security Audit — snyk — session-to-skill-extractor