supacortex
Pass
Audited by Gen Agent Trust Hub on Feb 26, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: Vulnerability to indirect prompt injection. The skill ingests data from untrusted sources such as bookmarks (URLs) and external conversation history. * Ingestion points:
scx bookmarks list,scx bookmarks get,scx conversation list,scx conversation get. * Boundary markers: Absent. There are no instructions to the agent to ignore or delimit embedded instructions in the fetched content. * Capability inventory: The skill can execute shell commands (Bash), write to the remote service (scx ... add/update), and fetch data. * Sanitization: Absent. The skill does not describe any sanitization of the input before it is processed or presented to the agent. - [COMMAND_EXECUTION]: Executes the
scxCLI commands to manage memory and bookmarks. * Evidence: Commands used includescx bookmarks,scx conversation, andscx identity. - [EXTERNAL_DOWNLOADS]: Fetches the CLI tool from the npm registry as part of the setup process. * Evidence: The skill documentation references
@supacortex/clifor installation. This is a vendor-owned resource.
Audit Metadata