ask-pplx
Warn
Audited by Snyk on Nov 21, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The workflow reads evidence the agent selects (code, specs, tests, measurements, and "retrieved material" or ticket text the agent supplies), and it names no monitored outsider-writable feed, so exposure to outsider text depends on the agent choosing to fetch it, which is low risk under recall-first scoring.
MEDIUM W013: Attempt to modify system services in skill instructions.
- Attempt to modify system services in skill instructions detected (low risk: 0.10). The skill can start a tracked
ollama serveprocess and stop an owned one, which changes the local service environment, but no explicit irreversible loss of operational state is established, so the gate for high or medium fails.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W013
MEDIUMAttempt to modify system services in skill instructions.
Audit Metadata