scikit-bio
Pass
Audited by Gen Agent Trust Hub on Jun 26, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is designed to ingest and process data from various external biological file formats (such as FASTA, FASTQ, Newick, and BIOM), which establishes a surface for indirect prompt injection if those files contain instructions the agent might interpret as its own.
- Ingestion points: Data ingestion occurs through standard library methods including
skbio.DNA.read,skbio.TreeNode.read, andskbio.Table.readas documented inSKILL.mdandreferences/api_reference.md. - Boundary markers: The skill instructions do not provide explicit delimiters or instructions for the agent to treat file contents as untrusted data rather than operational commands.
- Capability inventory: The skill's primary functions are limited to biological data manipulation and statistical calculations; it does not incorporate capabilities for network exfiltration, arbitrary shell execution, or privilege escalation.
- Sanitization: There is no evidence of specific sanitization, filtering, or validation processes for the textual content of the biological sequences or tables before they are processed by the agent.
Audit Metadata