ghost-inspector

Warn

Audited by Snyk on Apr 23, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.70). The SKILL.md explicitly allows the agent to proxy arbitrary requests to the Ghost Inspector API via "membrane request CONNECTION_ID /path/to/endpoint", which fetches third‑party (potentially user-generated) content that the agent is expected to read and act on (e.g., interpreting results and running follow-up actions).

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 23, 2026, 08:26 PM
Issues
1