The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests and processes log data from external sources using the oodle logs query command. This log data is considered untrusted and could contain malicious instructions designed to influence the agent's behavior.
Ingestion points: Output of oodle logs query -f query.ndjson -o json.
Boundary markers: None specified in the instructions to separate log content from agent instructions.
Capability inventory: The agent has the capability to execute shell commands and write files (cat > query.ndjson).
Sanitization: No explicit sanitization or validation of the log content is performed before processing.
[EXTERNAL_DOWNLOADS]: The skill requires the installation of the oodle CLI tool via Homebrew (brew install oodle-ai/oodle/oodle). This is a standard installation procedure for the vendor's tooling.
[COMMAND_EXECUTION]: The skill instructions involve executing the oodle CLI tool and using jq to parse JSON output. These are legitimate operations within the context of log management and data analysis.

oodle-logs