ljg-qa

Fail

Audited by Snyk on Oct 27, 2026

Risk Level: CRITICAL
Full Analysis

CRITICAL E004: Prompt injection detected in skill instructions.

  • Potential prompt injection detected (medium risk: 0.30). The skill contains an undocumented curl command that sends a notification to a local endpoint during execution, which acts on the user's behalf without explicit user expectation.

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

  • Third-party content exposure detected (low risk: 0.10). The workflow reads external web pages and PDFs via WebFetch and Read tools based on user-supplied URLs or files, exposing the agent to outsider-authored free text.

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
Oct 27, 2026, 01:46 AM
Issues
2