research-data-analysis
Pass
Audited by Gen Agent Trust Hub on May 20, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill architecture creates a surface for indirect prompt injection as it is designed to ingest and act upon untrusted external data.
- Ingestion points: The agent reads raw research datasets, data dictionaries, and source metadata (e.g., from arXiv, PubMed, or Zotero) stored in the
sources/anddata/directories as outlined inSKILL.mdandreferences/repository-contract.md. - Boundary markers: The skill lacks explicit instructions for using delimiters or boundary markers to differentiate data from instructions within the external sources.
- Capability inventory: The agent is authorized to write reusable analysis code in
src/, execute CLI tools, and update project-persistent knowledge bases inwiki/anddocs/according toSKILL.mdandreferences/output-contracts.md. - Sanitization: There are no defined procedures for sanitizing, validating, or escaping content from external sources before it influences code generation or documentation updates.
Audit Metadata