survey-generation

Pass

Audited by Gen Agent Trust Hub on Apr 21, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes a local Python script (search_semantic_scholar.py) belonging to the deep-research skill. This command is used to query academic databases for research papers, which is a standard operation within the skill's documented workflow.
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by ingesting paper titles and abstracts from external sources (Semantic Scholar/arXiv) and interpolating them into prompts. This risk is mitigated by the use of triple-dash (---) delimiters and the structured nature of the academic content being processed.
  • [DATA_EXFILTRATION]: The skill interacts with well-known academic services like Semantic Scholar and arXiv to fetch metadata. These operations are limited to data retrieval for the survey generation process and do not involve unauthorized exfiltration of sensitive user information.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 21, 2026, 07:28 AM