oodle-logs
Pass
Audited by Gen Agent Trust Hub on Jun 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
oodleCLI to perform log discovery and searching. It instructions the agent to execute local commands includingoodle logs index-patterns,oodle logs query,cat(for file creation), andjq(for data extraction). - [EXTERNAL_DOWNLOADS]: The skill recommends installing the
oodleCLI using Homebrew from the author's official tap (oodle-ai/oodle/oodle). This is a legitimate distribution channel for the vendor's tool. - [PROMPT_INJECTION]: The skill processes untrusted log data from OpenSearch, creating a surface for indirect prompt injection. Malicious content within the logs could attempt to influence the agent's logic during processing.
- Ingestion points: Log entries retrieved via
oodle logs query(SKILL.md). - Boundary markers: The instructions do not define explicit delimiters or warnings for the agent to ignore instructions embedded within the retrieved log data.
- Capability inventory: The skill environment allows shell command execution (
oodle), file system modification (cat), and data processing (jq). - Sanitization: There is no mention of content sanitization or filtering of the log data before it is presented to the agent.
Audit Metadata