gemini-cli-security

Fail

Audited by Snyk on Nov 10, 2026

Risk Level: CRITICAL
Full Analysis

CRITICAL E004: Prompt injection detected in skill instructions.

  • Potential prompt injection detected (medium risk: 0.30). The skill is a legitimate security scanner, but scripts/main.cjs hardcodes precision 0.9 and recall 0.93 into every JSON summary and markdown footer, so each run reports mock benchmark figures as if they were measured results, which is sketchy toward the user without indicating malicious intent.

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

  • Third-party content exposure detected (low risk: 0.10). The required workflow sends package names from the user's package.json to the OSV.dev querybatch API via WebFetch and ingests the returned advisory text, which is community-authored vulnerability data from a public database, so the agent consumes outsider text without choosing a specific item.

Issues (2)

E004
CRITICAL

Prompt injection detected in skill instructions.

W011
MEDIUM

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

Audit Metadata
Risk Level
CRITICAL
Analyzed
Nov 10, 2026, 12:12 PM
Issues
2