quantitative-researcher
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines workflows for sourcing and analyzing external market and macro datasets, which constitutes an ingestion surface for potential indirect prompt injection. However, the instructions emphasize data profiling, license checks, and reconciliation against multiple sources as defensive measures.
- Ingestion points: External market and macro datasets (referenced in SKILL.md and references/research_framing_and_data_quality.md).
- Boundary markers: The skill does not define specific prompt delimiters but relies on standard agent guardrails.
- Capability inventory: The skill uses standard agent capabilities for statistical analysis, notebook generation, and reporting.
- Sanitization: The skill mandates data profiling for missingness and outliers, as-of date tracking, and reconciliation spot-checks.
- [SAFE]: A thorough review of the skill's instructions, frontmatter, and reference files found no evidence of malicious behavior, including prompt injection, credential exfiltration, obfuscation, or unauthorized command execution.
Audit Metadata