value-dividend-screener

Fail

Audited by Gen Agent Trust Hub on Feb 21, 2026

Risk Level: HIGHCOMMAND_EXECUTION
Full Analysis
  • Persistence Mechanisms (HIGH): The file references/fmp_api_guide.md contains instructions to append command strings to shell configuration files to persist API keys across sessions.
  • Evidence: echo 'export FMP_API_KEY=your_api_key_here' >> ~/.bashrc in references/fmp_api_guide.md.
  • This technique allows for persistent environment modification and is a common vector for maintaining unauthorized access or execution in a shell environment.
  • Indirect Prompt Injection (LOW): The skill's primary function involves ingesting data from an external financial API (financialmodelingprep.com), which is an untrusted source.
  • Ingestion points: Data is retrieved from various endpoints such as /v3/stock-screener and /v3/income-statement/{symbol} as described in references/fmp_api_guide.md.
  • Boundary markers: There are no instructions in the provided files defining delimiters or warnings to ignore instructions embedded within the API responses.
  • Capability inventory: The skill uses the ingested data to perform complex financial analysis and ranking as described in references/screening_methodology.md.
  • Sanitization: No evidence of input validation or data sanitization is present in the provided documentation.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 21, 2026, 08:03 PM