scikit-bio
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted biological data from external files (e.g., FASTA, BIOM), creating an attack surface for indirect prompt injection. * Ingestion points: Functions like skbio.DNA.read() in SKILL.md and Table.read() in references/api_reference.md. * Boundary markers: Absent; there are no instructions for the agent to use delimiters or ignore embedded text in processed files. * Capability inventory: The skill utilizes file system reads/writes and Python execution for data analysis as described in SKILL.md. * Sanitization: Absent; the skill performs format parsing but does not sanitize content against natural language instructions.
Audit Metadata