Skills
skills/aaaaqwq/agi-super-skills/healthcare-monitor/Gen Agent Trust Hub

healthcare-monitor

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes external, untrusted data (business records and news snippets) and passes them into LLM prompts for analysis. \n
  • Ingestion points: Scraped content from various platforms enters the system via scripts/funding_detector_v2.py and is evaluated by the LLM in scripts/analyzer.py (using the analyze_with_llm function). \n
  • Boundary markers: The prompt construction in scripts/analyzer.py lacks clear delimiters or instructions to ignore potential commands embedded within the enterprise data. \n
  • Capability inventory: The skill has capabilities including network operations (scraping and notifications), file writing (reports and snapshots), and subprocess execution (credential retrieval via pass and notification pushing). \n
  • Sanitization: No sanitization or escaping of external content before interpolation into prompts was identified in the source code.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 10:14 PM