factor-research
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests instrument factor values and forward returns from external CSV files via the
factor_csvandreturn_csvparameters. This creates a potential surface for indirect prompt injection if the files were to contain malicious instructions instead of expected numeric data. - Ingestion points: Path parameters for factor and return data in the
factor_analysistool and variousquantlibmodule calls. - Boundary markers: The documentation does not specify the use of delimiters or specific safety instructions to isolate ingested data from the agent's prompt context.
- Capability inventory: The skill is capable of writing research artifacts to a user-defined
output_dirand performing complex statistical operations through thequantlib_calltool. - Sanitization: While the skill assumes valid aligned CSV structures (date index and instrument columns), there is no mention of explicit content sanitization for the data contained within the files.
- [DYNAMIC_EXECUTION]: The framework utilizes a
quantlib_callmechanism to dynamically load and execute specific mathematical modules for factor combination and neutralization. - Evidence: Files
references/combination.mdandreferences/neutralization.mddescribe using a JSON-based envelope to call internal functions such ascombine_factorsandneutralize_factor. - This represents a controlled and limited use of dynamic execution, as calls are restricted to pre-defined, platform-specific research modules rather than arbitrary user-supplied code.
Audit Metadata