tailor
Warn
Audited by Snyk on Jul 24, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). This workflow ingests outsider-authored free text from the adopter’s repository at runtime by scanning committed files (e.g.,
package.json, lockfiles, configs) to build the stack-fingerprint evidence table that is then included inscratchpad/tailor-proposal.mdfor the LLM to use.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata