data-sleuth
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill is composed of instructional markdown files and does not contain any executable code, scripts, or network-enabled tools. All analysis is performed using the agent's native reasoning capabilities.- [NO_CODE]: There are no source files, binaries, or shell scripts included in this skill. It functions solely as a prompt-engineering framework for data investigation.- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze user-provided data exports, which is a common surface for indirect prompt injection. However, it does not implement unsafe data handling practices or bypass existing safety protocols.
- Ingestion points: Structured user data and social media exports (SKILL.md).
- Boundary markers: Absent in instructions.
- Capability inventory: Uses native reasoning and built-in analysis tools.
- Sanitization: Handled by the underlying platform's safety guardrails.
Audit Metadata