financial-osint
Pass
Audited by Gen Agent Trust Hub on Jul 18, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill instructs the agent to search for and ingest content from various external websites and investigative databases (e.g., OpenCorporates, OCCRP Aleph). This processing of untrusted external data establishes a vulnerability surface for indirect prompt injection.
- Ingestion points: The workflow relies on WebFetch and WebSearch tools (as specified in the allowed-tools configuration) to pull data from third-party sources into the agent context.
- Boundary markers: No specific boundary markers or instructions to ignore potentially embedded commands within retrieved data are present in the methodology.
- Capability inventory: The skill environment permits the use of Bash for command execution and Write for file system operations, which could be targeted by a successful indirect injection attack.
- Sanitization: There are no instructions for sanitizing or validating the data retrieved from external sources before it is interpreted or processed by the agent.
Audit Metadata