pysam
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by processing untrusted genomic data files into the agent context.
- Ingestion points: External files such as BAM, VCF, and FASTA are read using
pysam.AlignmentFile,pysam.VariantFile, andpysam.FastaFileas described in the reference documentation files. - Boundary markers: The instructions do not define boundary markers or provide warnings to the agent to ignore embedded instructions within the genomic data.
- Capability inventory: The skill includes capabilities to write files to the system and execute shell commands through the
pysam.samtoolsandpysam.bcftoolswrappers. - Sanitization: No sanitization or validation logic is implemented for the content of the ingested sequencing files.
Audit Metadata