skills/freedomintelligence/openclaw-medical-skills/tooluniverse-expression-data-retrieval/Gen Agent Trust Hub
tooluniverse-expression-data-retrieval
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted metadata from external sources, making it susceptible to indirect prompt injection.\n
- Ingestion points: Dataset titles, descriptions, and sample annotations are retrieved from external APIs (ArrayExpress and BioStudies).\n
- Boundary markers: The skill does not use specific delimiters or instructions to isolate external content from the agent's context.\n
- Capability inventory: The skill utilizes tools for searching and fetching metadata; no high-risk capabilities like file system writes or arbitrary command execution are present.\n
- Sanitization: Metadata is included in the output without validation or escaping.\n- [EXTERNAL_DOWNLOADS]: The skill fetches scientific metadata and data file links from the European Bioinformatics Institute (ebi.ac.uk), which is a well-known and trusted service provider in the bioinformatics domain.
Audit Metadata