The Agent Skills Directory

[COMMAND_EXECUTION]: The SKILL.md file specifies Bash(cmd:*) in its allowed tools, which grants the agent the ability to execute arbitrary shell commands. While the provided Python scripts (analyze_text.py, summarize_text.py, translate_text.py) are benign templates for text analysis, the broad permission represents a significant capability surface.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core function of processing user-provided text. Ingestion points: Text files and inputs passed to the scripts in the scripts/ directory. Boundary markers: The instructions do not define delimiters or warnings to ignore instructions within the processed data. Capability inventory: The skill has access to Bash, Read, Grep, and Glob, allowing for file system access and command execution. Sanitization: No input sanitization or validation logic is present to filter potentially malicious instructions embedded in the analyzed text.

analyzing-text-with-nlp