infrahub-reporting-issues

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md workflow explicitly instructs the agent to query public GitHub content (step 4: "gh search issues" to pull matching issues) and to fetch repo issue templates via the gh API (step 6: fetch .github/ISSUE_TEMPLATE/bug_report.yml), which are untrusted, user-generated third‑party pages the agent must read and use to decide whether to comment vs open a new issue and to construct the issue body—creating a clear avenue for indirect prompt injection.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill explicitly fetches issue templates at runtime using the gh API command (e.g., "gh api repos///contents/.github/ISSUE_TEMPLATE/bug_report.yml --jq '.content' | base64 -d"), which pulls remote GitHub content that directly controls the structure/content of the generated issue (agent prompts/instructions).