geniml
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill facilitates the installation of the
genimlpackage directly from thedatabiorepository on GitHub and references theStarSpacetool from thefacebookresearchorganization as a necessary external dependency. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from multiple sources, creating a potential vector for indirect prompt injection.
- Ingestion points: Processes genomic
BEDfiles, metadataCSVfiles, andAnnData(.h5ad) files as seen inSKILL.md,references/bedspace.md, andreferences/scembed.md. - Boundary markers: Instructions do not include delimiters or specific guardrails to prevent the agent from following instructions that might be embedded in the genomic data or metadata labels.
- Capability inventory: The skill performs file system operations (writing BED/Parquet files), shell command execution (
uniwig,cat,genimlCLI), and network requests (fetching models from Hugging Face and BED files viaBBClient). - Sanitization: There is no evidence of validation or sanitization for the content of the ingested genomic or metadata files.
- [COMMAND_EXECUTION]: The skill documentation provides and expects the execution of several shell-based workflows, including package management with
uv, file concatenation withcat, and the use of specialized bioinformatics CLI tools likeuniwigand thegenimlsuite.
Audit Metadata