blogwatcher
Pass
Audited by Gen Agent Trust Hub on Apr 11, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the installation of a third-party binary from an external GitHub repository (github.com/Hyaxia/blogwatcher) using the go install command.
- [COMMAND_EXECUTION]: The skill uses the blogwatcher CLI tool to perform operations like scanning for updates and reading article content from external sources.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it fetches and processes content from external RSS/Atom feeds.
- Ingestion points: The scan and articles commands ingest data from external URLs (SKILL.md).
- Boundary markers: No delimiters or ignore-instructions warnings are present.
- Capability inventory: The agent can execute the blogwatcher command and read its output (SKILL.md).
- Sanitization: No sanitization or validation of the feed content is performed before processing.
Audit Metadata