tasks
Warn
Audited by Snyk on Jul 23, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.65). The required workflow reads
plan.mdandspec.md(outsider-authored free text category: wiki/issue-style authored by others), then writes derivedtasks.md, meaning the LLM context will include that outsider text when generating tasks.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata