stocktwits-sentiment

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches content from stocktwits.com to analyze market sentiment. This is a well-known service for financial social data.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user-generated content (message bodies) from StockTwits. An attacker could post messages containing malicious instructions that might influence the agent's behavior if the underlying model is not sufficiently robust.
  • Ingestion points: WebFetch of https://stocktwits.com/symbol/{ticker} (referenced in SKILL.md).
  • Boundary markers: Absent. The skill provides extraction instructions for the agent but does not explicitly wrap the fetched content in delimiters or include warnings to ignore embedded commands within the messages.
  • Capability inventory: Limited to data extraction and reporting via WebFetch. No high-privilege capabilities like file system modifications or arbitrary command execution are utilized.
  • Sanitization: No explicit sanitization or filtering of the extracted message bodies is defined.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 07:26 AM
Security Audit — agent-trust-hub — stocktwits-sentiment