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
Risk Level
SAFE
Analyzed
Jul 18, 2026, 12:06 AM
Security Audit — agent-trust-hub — financial-osint