skills/apache/magpie/announce-draft/Gen Agent Trust Hub

announce-draft

Pass

Audited by Gen Agent Trust Hub on Sep 24, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [Command Execution]: The skill executes a local pre-flight check using python3 -m setup_preflight with a locally defined PYTHONPATH. This is a standard operational pattern for the Magpie framework to verify project state before performing release tasks.
  • [Indirect Prompt Injection]: The skill processes untrusted external content, including planning issue bodies and changelogs. The instructions include explicit guardrails, directing the agent to treat all external text as data and never as instructions, which helps mitigate potential injection attempts.
  • [GitHub Tooling]: The skill uses the gh CLI to propose a pull request for site updates. This action is gated by a requirement for explicit user confirmation, ensuring that no state-changing operations occur without human review.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 24, 2026, 06:05 PM