Security issue: possible command injection in GitHub Actions workflow

Hello maintainers,

I would like to report a potential command-injection vulnerability in your GitHub Actions workflow.

The affected workflow file(s) invoke an LLM to process and summarize issues, and then directly concatenate the LLM output into a shell command argument for gh issue comment --body. Because untrusted model output is inserted into a shell command context, an attacker may craft a malicious issue so that the LLM response contains an injection payload.

Impact:

• Possible command injection during workflow execution.
• Possible leakage of sensitive environment variables (for example GITHUB_TOKEN or GH_TOKEN).
• Although these tokens are typically short-lived and scoped to workflow job/step execution, an attacker may attempt to prolong execution time (for example via sleep-based techniques) and abuse the token during that window.

Recommended remediation:

• Do not place ${{ steps.inference.outputs.response }} directly in a shell command argument.
• Pass it through a step environment variable first (for example RESPONSE).
• In shell, reference it only as a double-quoted variable (for example "$RESPONSE").

Affected workflow file(s) observed:

• https://github.com/jd-opensource/jd-github-template/blob/6656b21cf8dfb9de5b2f7707a3ad294820c59902/.github/workflows/summary.yml

Thank you for your time and for maintaining this project.

Inizia leggendo .github/workflows/summary.yml al commit indicato, concentrandoti su come la risposta dell’inferenza viene passata a gh issue comment --body. Conferma che l’output non attendibile venga trasferito tramite una variabile d’ambiente e referenziato come variabile shell tra virgolette. Il lavoro è completato quando il workflow non inserisce più direttamente l’output dell’inferenza nel contesto di un comando shell.