The Agent Skills Directory

[EXTERNAL_DOWNLOADS] (LOW): The scripts require the ete3 Python library. While a standard tool in bioinformatics, it is an external dependency not found in the trusted repository list provided in the instructions.
[PROMPT_INJECTION] (LOW): The skill possesses an indirect prompt injection surface because it processes untrusted Newick-format tree files which may contain malicious instructions in node or leaf labels.
Ingestion points: Files are loaded via ete3.Tree in scripts/quick_visualize.py and scripts/tree_operations.py.
Boundary markers: Absent; there are no delimiters or warnings to separate processed tree data from the agent's instruction context.
Capability inventory: The scripts can perform file writes (tree.write, tree.render) and output content to the console, providing a potential path for data manipulation if an agent follows instructions embedded in tree data.
Sanitization: No validation, escaping, or sanitization of tree labels or metadata is performed before the data is processed or output.
[DATA_EXFILTRATION] (SAFE): No unauthorized network activity or access to hardcoded sensitive files was detected. File operations are performed on paths specified by user arguments for intended functionality.
[COMMAND_EXECUTION] (SAFE): The scripts use argparse with strict type casting (e.g., int for dimensions) and do not utilize dangerous functions like eval() or os.system() to process inputs.

etetoolkit