deepagents-filesystem
Warn
Audited by Snyk on Aug 16, 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 skill’s runtime workflow ingests only the agent’s caller-provided
messagesand may then use filesystem tools (e.g.,read_file/write_file) to act on paths, so outsider-authored free text is directly available to the model for decision-making.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata