qimao-novel-scraper

Pass

Audited by Gen Agent Trust Hub on Aug 8, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the browser_run_code_unsafe tool to execute specific JavaScript snippets for DOM traversal and data extraction within the browser environment.
  • [EXTERNAL_DOWNLOADS]: The skill retrieves data from qimao.com to analyze novel rankings and content. This is consistent with the skill's stated purpose of novel scraping and analysis.
  • [PROMPT_INJECTION]: The skill processes untrusted external content from novel summaries and chapters, which presents a surface for indirect prompt injection.
  • Ingestion points: Scraped book titles, descriptions, and the full text of the first three chapters from qimao.com (referenced in SKILL.md).
  • Boundary markers: Absent; instructions do not specify the use of delimiters or warnings to the agent to ignore instructions embedded in the novel text.
  • Capability inventory: Uses playwright tools (browser_navigate, browser_run_code_unsafe) and writes results to the local filesystem under the 小说扫榜\七猫小说\ directory.
  • Sanitization: No explicit sanitization or validation of the scraped text is described in the standard workflow.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 8, 2026, 11:27 PM
Security Audit — agent-trust-hub — qimao-novel-scraper