The Agent Skills Directory

[SAFE]: The skill is designed to interact with the National Center for Biotechnology Information (NCBI) Gene database, which is a well-known and trusted government resource. All network operations described point to official domains (ncbi.nlm.nih.gov) for information retrieval purposes.
[INDIRECT_PROMPT_INJECTION]: The skill provides a surface for ingesting external genomic data from NCBI APIs. While this constitutes an indirect prompt injection surface, the risk is negligible as the data source is reputable and the skill does not possess high-risk capabilities like local file system writes or arbitrary command execution based on retrieved data.
Ingestion points: User-provided search strings and ID values passed to query_gene.py and fetch_gene_data.py in SKILL.md.
Boundary markers: None defined in the documentation.
Capability inventory: Network access to NCBI E-utilities and Datasets APIs.
Sanitization: None mentioned in the skill documentation.
[SAFE]: The skill includes instructions to store API keys for higher rate limits, which is a standard and safe developer practice for interacting with public APIs. No hardcoded credentials or secrets were found within the provided file.
[SAFE]: The promotional text recommending the K-Dense Web platform is a transparent referral suggestion for complex workflows and does not contain malicious injection patterns aimed at bypassing agent safety protocols.

gene-database