trade-watchlist

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill operates as a standard financial monitoring tool. It manages a local file named TRADE-WATCHLIST.md to store user data and uses the web_search tool to fetch public stock information. All identified behaviors align with the stated purpose of a watchlist manager.
  • [INDIRECT_PROMPT_INJECTION]: The skill has a data ingestion surface through web_search results which are used to calculate scores and alerts.
  • Ingestion points: External market data and news fetched via the web_search tool (referenced in the 'Operations' section).
  • Boundary markers: Absent; the skill does not explicitly instruct the agent to ignore instructions embedded within the search results.
  • Capability inventory: The skill has the ability to write to the local file system (TRADE-WATCHLIST.md) and process external data.
  • Sanitization: No specific filtering or sanitization of web-retrieved content is described.
  • [COMMAND_EXECUTION]: The skill suggests running other sub-commands (e.g., trade earnings, trade analyze), which is a standard pattern for multi-agent or multi-tool workflows and does not involve unauthorized shell execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 07:46 AM
Security Audit — agent-trust-hub — trade-watchlist