skills/zju-real/easel/redbook/Gen Agent Trust Hub

redbook

Warn

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONDYNAMIC_EXECUTIONDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [DYNAMIC_EXECUTION]: The scripts/postinstall.js script programmatically modifies the source code of the @steipete/sweet-cookie dependency within the node_modules directory during installation. It uses writeFileSync to patch chromeSqliteMac.js and shared.js to address keychain timeouts and data type overflows.
  • [COMMAND_EXECUTION]: The skill uses child_process.spawn and execFileSync in src/lib/cdp-cookies.ts to search for Chrome binaries and launch them with remote debugging enabled. It also utilizes puppeteer-core in src/lib/render.ts to launch a headless browser for rendering content cards.
  • [DATA_EXFILTRATION]: The skill accesses highly sensitive local files including Chrome's Local State and Cookies SQLite databases across macOS, Windows, and Linux to extract authentication tokens. It also attempts to access the macOS Keychain via its dependencies to decrypt these credentials. While the data is sent to the official xiaohongshu.com and rednote.com domains, the extraction of session cookies from the local environment is a high-privilege action.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process large volumes of untrusted data from Xiaohongshu notes and user comments. This ingestion creates an attack surface where malicious content embedded in notes could influence the agent's behavior, although the skill includes instructions for paced research loops to mitigate simple automated exploitation.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Sep 2, 2026, 01:22 PM