The Agent Skills Directory

[COMMAND_EXECUTION]: The initialization scripts scripts/setup_elk.py, scripts/setup_loki.py, and scripts/setup_splunk.py accept a --project argument that is used to construct file system paths without sanitization. Using Path(output_dir) / project_name allows a user to provide an absolute path or a path with parent directory references (e.g., ../../) to create directories and write initialization files outside of the intended project scope.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest user-specified infrastructure details and log formats to generate configuration files and deployment commands, creating a vulnerability surface where malicious input could influence agent actions.
Ingestion points: User prompts defining the log aggregation platform, storage requirements, and parsing rules as described in SKILL.md.
Boundary markers: The instructions do not define delimiters or warnings to ignore instructions embedded in the logs or user-provided configuration snippets.
Capability inventory: The skill utilizes powerful tools including Bash(docker:*), Bash(kubectl:*), and file write operations.
Sanitization: There is no evidence of input validation or escaping for the parameters interpolated into generated configurations or shell commands.

setting-up-log-aggregation