alterlab-eda
Pass
Audited by Gen Agent Trust Hub on Apr 12, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection (Category 8) through its ingestion of untrusted scientific data files. Each file format processed by the skill can contain metadata fields that are extracted and rendered into a final markdown report.
- Ingestion points: The
scripts/eda_analyzer.pyscript reads from various scientific file formats (e.g., FASTQ, PDB, CSV) provided by the user. - Boundary markers: The skill uses markdown headers and code blocks in its report template to separate data, which provides basic structural delimitation but does not sanitize content.
- Capability inventory: The skill uses a local Python script for analysis and has the capability to read and write files on the local file system.
- Sanitization: There is no evidence of sanitization or filtering applied to text fields extracted from scientific files before they are included in the generated report.
Audit Metadata