alterlab-qiime2-amplicon
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill facilitates the download of conda environment configuration files and reference datasets from the official QIIME 2 GitHub repository and associated domains. These resources are necessary for the skill's primary function and come from a well-known scientific software provider.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests external data files, creating a potential surface for indirect prompt injection.
- Ingestion points: Processes filename patterns in local directories using
scripts/make_manifest.pyand reads metadata and provenance logs from QIIME 2 artifacts usingscripts/check_artifact.py. - Boundary markers: No explicit delimiters or safety instructions are used to separate user-provided file content from the agent's logic.
- Capability inventory: The skill utilizes
Bashfor system environment management and execution of complex bioinformatics tools. - Sanitization: Scripts perform structural parsing of scientific files but do not explicitly sanitize content for adversarial natural language instructions.
Audit Metadata