ledger-driven-repo-forensic-recovery-skill

Fail

Audited by Snyk on Apr 15, 2026

Risk Level: HIGH
Full Analysis

HIGH W007: Insecure credential handling detected in skill instructions.

  • Insecure credential handling detected (high risk: 0.90). This skill requires reading and presenting raw samples, terminal histories, clipboard and assistant session files and to produce file-and-line "proof" without any redact rules, so it can force the model to include secrets (API keys, tokens, passwords) verbatim from those sources.

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

  • Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md explicitly instructs ingesting external user-generated sources — notably remote GitHub PRs/branches via "gh pr list/view" and remote commit/PR surfaces and assistant session histories and clipboard files under "Source Coverage" and "Git and remote collaboration evidence" — and then uses those contents to decide and execute restorations, so untrusted third-party content can directly influence tool actions.

Issues (2)

W007
HIGH

Insecure credential handling detected in skill instructions.

W011
MEDIUM

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

Audit Metadata
Risk Level
HIGH
Analyzed
Apr 15, 2026, 11:31 AM
Issues
2