skills/lijigang/ljg-skills/ljg-qa/Gen Agent Trust Hub

ljg-qa

Pass

Audited by Gen Agent Trust Hub on Oct 27, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external content from URLs (via WebFetch) and PDF files (via Read tool) to extract information. This creates a surface for indirect prompt injection where malicious instructions embedded in a processed document could attempt to influence the agent's output or logic.
  • Ingestion points: Workflows/Extract.md (Step 1) details fetching content from URLs, arXiv links, and local PDFs.
  • Boundary markers: The instructions do not define specific delimiters (e.g., XML tags or clear separators) to isolate external content from the skill's operational instructions.
  • Capability inventory: The skill utilizes WebFetch, Read, WebSearch, file writing to ~/Documents/notes/, and shell execution for notifications.
  • Sanitization: There is no evidence of sanitization or filtering applied to the external content before it is processed by the LLM.
  • [COMMAND_EXECUTION]: The skill instructions include shell commands intended to be executed during the workflow. Specifically, it uses curl to send a POST request to http://localhost:31337/notify and the date command for generating timestamps. While targeting localhost is generally considered low-risk for exfiltration, this establishes a pattern of side-effect execution on the local environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 27, 2026, 01:46 AM