alterlab-rnaseq-quant
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or data exfiltration attempts were detected. The skill instructions and scripts are focused entirely on legitimate bioinformatics workflows.
- [COMMAND_EXECUTION]: The skill facilitates the execution of local bioinformatics command-line tools (salmon, kallisto, kb-python). These operations are standard scientific procedures and are appropriately documented.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests external data (FASTA, GTF, quant files). 1. Ingestion points: files processed by scripts/make_decoys.py, scripts/build_tx2gene.py, and scripts/import_quant.py. 2. Boundary markers: absent. 3. Capability inventory: file read, write, and bash execution for bioinformatics toolsets. 4. Sanitization: none, scripts use standard parsing. The risk is assessed as low as no data is interpolated into instructions or executed dynamically.
Audit Metadata