extract-data
Pass
Audited by Gen Agent Trust Hub on Jul 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security threats identified. The skill defines a subagent prompt for extracting information from research papers and does not utilize any tools or scripts.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted external data (
paper_contents). While the prompt lacks explicit boundary markers to isolate this data, the skill has no functional capabilities (such as network access, file system writes, or command execution) that could be leveraged if an injection occurred. The impact is limited to the quality of the generated summary.
Audit Metadata