blogwatcher
Warn
Audited by Gen Agent Trust Hub on Feb 15, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS] (MEDIUM): The skill installs the
blogwatcherCLI tool fromgithub.com/Hyaxia/blogwatcher. This repository is not part of the trusted organizations list, meaning the code being installed and executed has not been verified. - [COMMAND_EXECUTION] (LOW): The skill relies on executing the
blogwatchercommand-line utility to perform its functions. - [INDIRECT_PROMPT_INJECTION] (LOW): The skill is designed to ingest and process untrusted data from external RSS/Atom feeds.
- Ingestion points: Data enters the system via the
blogwatcher scanandblogwatcher articlescommands, which fetch remote XML/HTML content. - Boundary markers: There are no specified delimiters or instructions to ignore embedded content in the documentation.
- Capability inventory: The skill executes local commands and manages a local database of blogs and articles.
- Sanitization: Sanitization is handled internally by the
blogwatcherbinary, which is opaque to the agent.
Audit Metadata