The Agent Skills Directory

[PRIVILEGE_ESCALATION]: The skill instructs the agent to use elevated privileges to install system libraries on Linux systems.
Evidence: sudo apt install libta-lib-dev and sudo apt update && sudo apt install build-essential libta-lib-dev in the Failure modes section.
[INDIRECT_PROMPT_INJECTION]: The skill processes external files that could contain malicious instructions if the files are modified by an attacker.
Ingestion points: The agent is instructed to read requirements.txt for package installation and .env.sample for environment configuration.
Boundary markers: Absent. No specific delimiters or instructions are provided to the agent to ignore potential instructions embedded in these files.
Capability inventory: The skill has access to Bash, Write, and Edit tools, allowing it to execute arbitrary shell commands and modify local files based on the processed data.
Sanitization: Absent. There is no mention of validating or sanitizing the content of the external files before processing them.
[COMMAND_EXECUTION]: The skill uses the Bash tool to perform a variety of system operations.
Evidence: Commands for OS detection (uname -s), virtual environment creation (python -m venv venv), and Python package installation (pip install -r requirements.txt).

algo-setup