data-analyst
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze user-supplied data (CSV, JSON, Excel, etc.) but lacks explicit instructions to treat this content as inert data. This creates a surface where malicious instructions embedded in a data file could be interpreted by the agent as commands.
- Ingestion points: User-provided data files or snippets processed during the cleaning and analysis phases (SKILL.md).
- Boundary markers: Absent; the skill does not define delimiters (like XML tags or specific markers) to wrap data or include instructions to ignore commands within the data.
- Capability inventory: The skill is capable of generating analysis code in Python and SQL (SKILL.md, Ability Boundary).
- Sanitization: No sanitization or validation logic is specified for the input data.
- [EXTERNAL_DOWNLOADS]: The skill includes a rule to recommend the installation of an external skill repository (
github:mindverse/skillhub) when the user's requirements exceed its built-in capabilities. This recommendation is made transparently to the user via the platform's installation command.
Audit Metadata