outline-cli
Pass
Audited by Gen Agent Trust Hub on Jun 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTIONREMOTE_CODE_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
olcommand-line interface to perform search and management operations on Outline wiki documents and collections, including destructive actions likeol doc deleteandol col deletewith the--confirmflag. - [EXTERNAL_DOWNLOADS]: Documents the use of the
ol updatecommand, which allows the CLI to fetch and install software updates from its official distribution channels. - [REMOTE_CODE_EXECUTION]: The
ol updatefunctionality represents a mechanism for downloading and executing updated code for the CLI tool from the developer's infrastructure. - [PROMPT_INJECTION]: The skill processes documents and metadata from an external wiki instance (e.g., via
ol doc get), which creates an indirect prompt injection surface where adversarial content could attempt to influence agent behavior. - Ingestion points: Markdown wiki documents retrieved via
ol doc get,ol search, andol doc list. - Boundary markers: No explicit delimiters or instruction isolation warnings are provided in the skill documentation.
- Capability inventory: Full CRUD (Create, Read, Update, Delete) operations on documents and collections.
- Sanitization: There is no mention of sanitization or filtering applied to the retrieved markdown content before it enters the agent's context.
Audit Metadata