resolve-linear-tech-debt

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.85). The workflow ingests outsider-authored free text from Linear issues: it lists issues via mcp__linear-server__list_issues(...) and then (in Step 2/3) uses the issue’s title/body/content for assessment and code exploration, which becomes LLM-readable context; Linear issue text is authored by non-operating-user parties.

MEDIUM W021: Hidden or invisible Unicode characters detected (potential obfuscation or prompt injection).

• Hidden Unicode characters detected (1 type(s) found)