qrspi-create-research-questions

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

• Third-party content exposure detected (high risk: 0.70). The skill’s runtime workflow reads a user-provided ticket (file path / GitHub issue / Linear ticket / inline text) via a Read tool and then generates questions; if that ticket body/comments are authored by an outsider, their free-form text is ingested into the LLM context during ticket analysis (Step 1–2).

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.80). The skill fetches ticket text at runtime from external sources (e.g., GitHub issue URLs such as owner/repo#123 via the "gh issue view" command and Linear ticket IDs via the Linear API) and uses that fetched content to directly drive the generated research questions (i.e., agent prompts), so those external URLs control runtime prompts.