biopython
Pass
Audited by Gen Agent Trust Hub on Apr 16, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides instructions to install the 'biopython' library from the public Python Package Index (PyPI) registry using the 'uv' package manager.
- [COMMAND_EXECUTION]: The documentation includes examples of using shell commands such as 'grep' for searching local documentation files and 'uv' for installing dependencies.
- [PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection by instructing the agent to parse and process content from external biological file formats and database responses.
- Ingestion points: Untrusted data enters the agent context through 'SeqIO.parse', 'Entrez.read', 'NCBIXML.read', and 'Phylo.read' operations documented in 'SKILL.md'.
- Boundary markers: The skill does not provide instructions or examples for using delimiters or boundary markers to separate ingested data from agent instructions.
- Capability inventory: The skill grants the agent network access capabilities via 'Bio.Entrez' and 'Bio.Blast', and file system access for reading and writing biological records.
- Sanitization: No instructions for sanitizing, escaping, or validating the content of the parsed records are provided before the data is processed by the agent.
Audit Metadata