blogwatcher
Pass
Audited by Gen Agent Trust Hub on Mar 6, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill download and installs the
blogwatcherCLI tool from a third-party GitHub repository (github.com/Hyaxia/blogwatcher) using the Go toolchain. - [COMMAND_EXECUTION]: The skill relies on executing the
blogwatcherbinary locally to manage and scan blog feeds. - [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by ingesting untrusted data from external RSS/Atom feeds.
- Ingestion points: Content from external feeds is brought into the agent context through the
blogwatcher articlesandblogwatcher scancommands. - Boundary markers: The skill does not define specific delimiters or instructions to prevent the agent from following commands embedded within the blog content.
- Capability inventory: The agent has the capability to execute the
blogwatchertool and potentially other system commands based on the output it processes. - Sanitization: There is no evidence of sanitization or filtering of the feed content before it is presented to the agent.
Audit Metadata