skills/freedomintelligence/openclaw-medical-skills/tooluniverse-sequence-retrieval/Gen Agent Trust Hub
tooluniverse-sequence-retrieval
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection via the ingestion of biological metadata from external public sources.
- Ingestion points: Data is retrieved from NCBI and ENA databases via tool calls such as
NCBI_search_nucleotide,NCBI_get_sequence, andena_get_entryas defined inSKILL.md. - Boundary markers: Retrieved content is placed within Markdown code blocks (e.g., FASTA) and tables in the output report, but the instructions do not include specific delimiters or directives for the agent to disregard instructions potentially present in the biological data fields.
- Capability inventory: The skill uses network-connected tools provided by the
tooluniverseframework to fetch and display extensive biological datasets inSKILL.md. - Sanitization: There is no specification for sanitizing or filtering input from the external database APIs (such as sequence descriptions or genomic feature annotations) before they are presented to the agent.
Audit Metadata