qiime2-amplicon
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The script
scripts/amplicon_workflow.pyexecutes QIIME 2 commands viasubprocess.run. The implementation follows security best practices by using argument lists instead of shell strings to prevent injection, though it allows the executable path to be configured via command-line arguments. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted external data, including manifest files and sample metadata, which could serve as a vector for indirect prompt injection if the output is processed by the agent. \n
- Ingestion points: Manifest and metadata files read in
scripts/amplicon_workflow.py. \n - Boundary markers: None identified. \n
- Capability inventory: Command execution via
subprocess.runinscripts/amplicon_workflow.py. \n - Sanitization: Basic format and biological character validation are present, but the script does not sanitize against potential natural language instructions embedded in data fields.
Audit Metadata