academic-paper-writer-pro-2

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

• Third-party content exposure detected (high risk: 0.80). The skill's workflows explicitly instruct the Agent to fetch and use open web content (e.g., SKILL.md / content_generation/SKILL.md: "先调用互联网搜索查证最权威的高清架构原理图", SKILL.md §1.0 auto-update: git fetch .../git pull, and TROUBLESHOOTING.md: "Verify all references against Google Scholar"), meaning the agent will ingest untrusted public third‑party content that can influence generation and tool actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly performs runtime auto-update/install commands (e.g., "git pull" or "npx skills add https://github.com/BoHeFan/academic-paper-writer-pro-2 --skill academic-paper-writer-pro") which will fetch remote repository code during execution and can cause remote code to be run or control agent behavior.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (high risk: 0.70). The skill instructs the agent to modify local files (git pull/pack/unpack, rm -rf resources/), run arbitrary npx/python commands and explicitly recommends disabling Chromium sandbox flags ("--no-sandbox", "--disable-setuid-sandbox"), which is a direct instruction to bypass a security mechanism even though it does not request sudo or create system users.