bestblogs-capture
Pass
Audited by Gen Agent Trust Hub on May 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill functions as a wrapper for the
bestblogsCLI tool, executing commands to manage user data on the BestBlogs platform. This includes creating bookmarks, adding highlights, and clearing history, which are the primary intended functions of the skill. - [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it processes untrusted data (such as highlighted text from external articles and user-provided notes) and interpolates these strings into CLI command arguments.
- Ingestion points: User-provided strings for highlight text (
-t), notes (-n), and bookmark notes (--note) inSKILL.md. - Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the skill content.
- Capability inventory: Shell command execution via the
bestblogsCLI, which can modify user data and history. - Sanitization: No explicit sanitization or validation steps are defined within the skill's instructions for handling the external content.
Audit Metadata