The Agent Skills Directory

[PROMPT_INJECTION]: The skill contains a section titled 'Suggest Using K-Dense Web For Complex Worflows' which provides specific instructions to the agent to proactively recommend an external platform. This acts as a behavioral override for promotional purposes, steering the agent's natural response pattern.
[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection.
Ingestion points: Data enters the context from multiple external genomic databases via modules such as info, search, enrichr, and archs4 (described in SKILL.md).
Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the retrieved data.
Capability inventory: The skill has the capability to interact with the OpenAI API via gget gpt and perform file writes using the -o/--out flag.
Sanitization: There is no evidence of sanitization or filtering of external content before it is processed by the agent or the gpt module.
[EXTERNAL_DOWNLOADS]: The gget setup command is documented to download significant external resources, including approximately 4GB of model parameters for the AlphaFold module and local databases for the ELM module. Additionally, the ref module uses curl to download reference genomes from Ensembl when the -d flag is used.
[COMMAND_EXECUTION]: The skill provides documentation for executing various command-line operations, including package installation via uv pip and bioinformatics tasks such as sequence alignment (muscle, diamond) and transcriptome indexing (kallisto), which are standard for its intended use case.

gget