filesystem-context

Warn

Audited by Snyk on Jun 30, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (medium risk: 0.65). The skill’s runtime path ToolOutputHandler.process_output() / ScratchPadManager.offload() takes arbitrary tool output strings (which commonly include outsider-authored free text such as scraped web pages or user messages) and writes them to scratch files, then returns a context-visible reference/summary that the agent can read—so outsider text can enter the LLM context indirectly via tool outputs.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 30, 2026, 09:38 AM
Issues
1
Security Audit — snyk — filesystem-context