microbiologist
Pass
Audited by Gen Agent Trust Hub on Aug 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill contains comprehensive guidelines for scientific reasoning, experimental design, and data interpretation in microbiology. It does not include executable code, hidden payloads, or suspicious instructions.
- [INDIRECT_PROMPT_INJECTION]: The skill instructions define workflows for processing external biological data, which inherently presents a potential surface for indirect prompt injection.
- Ingestion points: The agent is instructed to process various sequencing and metadata files such as FASTQ, FASTA, BIOM, and TSV as described in
SKILL.md. - Boundary markers: No explicit markers or delimiters are provided in the instructions to separate data from system prompts.
- Capability inventory: The skill references the use of several bioinformatics CLI tools and pipelines (e.g., Kraken2, QIIME2, metaSPAdes) for analysis.
- Sanitization: There are no instructions for sanitizing or validating the contents of these external files before processing.
Audit Metadata