promptlens
Warn
Audited by Snyk on Aug 6, 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). PromptLens ingests user-authored message text from locally stored agent history files/DBs (e.g., Codex
history.jsonl/session*.jsonl, Claudehistory.jsonl, OpenCodeopencode.db, OpenClawopenclaw-agent.sqlite, Hermesstate.db, or arbitrary--pathcustom fixtures) and tokenizes/cleans that text at runtime, so an outsider who can submit/poison messages into those monitored histories can affect what the script reads.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata