blogwatcher
Pass
Audited by Gen Agent Trust Hub on Mar 9, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill installs the
blogwatcherbinary from a third-party GitHub repository (github.com/Hyaxia/blogwatcher) that is not part of the trusted vendors list. - [COMMAND_EXECUTION]: The skill executes the
blogwatchercommand-line interface to manage blogs and scan for new articles. - [PROMPT_INJECTION]: There is a risk of indirect prompt injection where malicious instructions embedded in a blog's RSS or Atom feed could influence the AI agent's behavior. Ingestion points: Data enters the system from external URLs via the
scanandarticlescommands. Boundary markers: The skill does not define any delimiters or instructions for the agent to ignore embedded commands in the feed data. Capability inventory: The agent can execute commands through theblogwatcherCLI. Sanitization: No sanitization of the external feed content is performed before it is presented to the agent.
Audit Metadata