blogwatcher

Warn

Audited by Gen Agent Trust Hub on Feb 23, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of a Go module from a third-party repository (github.com/Hyaxia/blogwatcher/cmd/blogwatcher@latest). This source is not part of the trusted organization list or recognized as a well-known service.
  • [COMMAND_EXECUTION]: The skill relies on the execution of the blogwatcher binary, which is compiled and installed from an external source.
  • [PROMPT_INJECTION]: The skill processes untrusted data from RSS and Atom feeds, creating a surface for indirect prompt injection.
  • Ingestion points: Data enters the agent's context through the scan and articles commands which fetch content from external URLs.
  • Boundary markers: There are no specific delimiters or instructional barriers defined in the skill to prevent the agent from following instructions hidden within feed content.
  • Capability inventory: The skill executes a custom binary and performs network operations.
  • Sanitization: No sanitization or filtering logic is specified for the data retrieved from external feeds.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 23, 2026, 12:56 PM