branch
Warn
Audited by Snyk on Aug 8, 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). In create/update/coord modes the workflow writes user-supplied free text (e.g.,
--description "<text>",--working-on,--next,--blocked-by,--asks,coord <message>) into the journal file$JOURNAL = ~/.claude/coordination/<repo>/journal.md, so an outsider can inject arbitrary text that is then ingested by later/branch listruns when the agent reads$JOURNALto displaydescriptionand active-entry fields.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata