invest-macro
Pass
Audited by Gen Agent Trust Hub on Nov 21, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using
invest-cliand a fallback Python script located at$HOME/.agents/skills/invest-cli/scripts/invest_cli.py. These commands are used to retrieve economic indicators and are considered legitimate vendor-owned tools within the skill's ecosystem. - [INDIRECT_PROMPT_INJECTION]: The skill processes data fetched from external sources including the Federal Reserve Economic Data (FRED) API, Wind economic data, and general public retrieval services. This represents a potential vulnerability surface where untrusted data could attempt to influence the agent's logic.
- Ingestion points: Economic data retrieved via the
invest-cli intent macroandinvest-cli wind economic_datacommands. - Boundary markers: Absent; the provided instructions do not include specific delimiters or warnings to the agent to disregard embedded instructions within the retrieved data.
- Capability inventory: The agent has the capability to execute shell commands (
invest-cli,python3) and access local file system paths. - Sanitization: Absent; there is no mention of sanitization, validation, or escaping logic applied to the external data before it is processed by the agent.
Audit Metadata