doko-page-reader
Pass
Audited by Gen Agent Trust Hub on Apr 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
dokobotCLI to perform browser automation and content extraction on the user's local machine. - [EXTERNAL_DOWNLOADS]: The instructions reference the installation of external components, specifically the
dokobotCLI and its associated local bridge. - [PROMPT_INJECTION]: The skill processes untrusted data from external websites, which serves as a vector for indirect prompt injection.
- Ingestion points: Data enters the context from arbitrary URLs via the
dokobot doko readcommand inSKILL.md. - Boundary markers: None are present; the skill lacks delimiters or instructions to ignore commands within the extracted web content.
- Capability inventory: The skill maintains the ability to execute shell commands via the
dokobotutility as documented inSKILL.md. - Sanitization: No evidence of sanitization, filtering, or validation of the ingested web content is provided.
Audit Metadata