context-crusher
Warn
Audited by Snyk on Aug 13, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The runtime workflow reads the user-supplied payload from a specified local file path or stdin (
--fileread atscripts/context_crush.py:112) and then compresses it before sending to the LLM, so attacker-authored free text can reach the LLM via that payload.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata