investigation-loop
Warn
Audited by Snyk on Aug 17, 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 investigation-loop skill instructs the agent to “read the ticket” (Jira
<TICKET-KEY>) and then “walks linked tickets and the relevant code,” meaning outsider-authored free text from Jira tickets/linked items can be ingested at runtime without prior selection of specific content.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata