market-trend-analysis

Pass

Audited by Gen Agent Trust Hub on Mar 8, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core function of processing untrusted external data.
  • Ingestion points: The skill accepts an array of articles containing titles and content from sources like news sites, GitHub, and RSS feeds as defined in SKILL.md.
  • Boundary markers: No explicit boundary markers or instructions to disregard embedded commands were identified in the script logic or the prompt structure.
  • Capability inventory: The skill is authorized to use Bash, Read, and Write tools, which increases the potential impact of a successful injection.
  • Sanitization: While scripts/extract_keywords.py performs basic tokenization by filtering non-word characters, the raw article content is used for LLM-driven trend scoring and sentiment analysis without sufficient sanitization to prevent instruction-based attacks.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 8, 2026, 07:19 AM