alterlab-nmc-data-journalist
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted external data (public datasets and web search results) as part of its primary data journalism function.
- Ingestion points: The agent is instructed to perform web searches for datasets and read project files from the user's directory.
- Boundary markers: There are no explicit instructions to use delimiters or markers to isolate external data from its core instructions.
- Capability inventory: The skill is limited to searching, reading files, and writing markdown deliverables. It does not utilize high-risk tools for arbitrary command execution or network exfiltration of sensitive files.
- Sanitization: No explicit sanitization or filtering logic is present for processing external content.
Audit Metadata