backlinks-timeseries-summary
Warn
Audited by Snyk on Jul 15, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). The required workflow calls a runtime HTTP endpoint (curl to
https://ai-factory.frevana.com/service/backlinks/timeseries-summary), then reads the returned response body as text (python3 ... response_path.read_text(...)) and injects it into the agent context by printing it to stdout (cat "$RESULT_FILE"), so outsider-authored free text from the provider can reach the LLM.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata