blogwatcher
Warn
Audited by Gen Agent Trust Hub on Mar 14, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill installs a binary from an untrusted third-party repository: github.com/Hyaxia/blogwatcher/cmd/blogwatcher@latest.
- [COMMAND_EXECUTION]: The skill relies on executing the 'blogwatcher' binary, which is an externally sourced tool.
- [PROMPT_INJECTION]: Potential for indirect prompt injection as the skill processes untrusted content from external RSS/Atom feeds. Ingestion points: Feed data is retrieved via 'blogwatcher scan' and 'blogwatcher articles' commands. Boundary markers: No boundary markers are used when processing feed content. Capability inventory: The skill executes local binary commands. Sanitization: There is no evidence of sanitization of external feed content.
Audit Metadata