stocktwits-sentiment

Pass

Audited by Gen Agent Trust Hub on Mar 28, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill retrieves data from StockTwits, a well-known financial platform, to perform sentiment analysis on stock tickers.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it extracts and processes user-generated message bodies.
  • Ingestion points: Untrusted text from StockTwits message boards is ingested into the agent context through the WebFetch instructions in SKILL.md.
  • Boundary markers: The extraction prompt does not include delimiters or specific instructions to ignore malicious commands that might be embedded in the scraped messages.
  • Capability inventory: The skill's capabilities are limited to scoring and data presentation, with no access to sensitive system tools, files, or network exfiltration paths.
  • Sanitization: Scraped message bodies are used directly in the output without validation or filtering.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 28, 2026, 12:14 AM