blogwatcher
Pass
Audited by Gen Agent Trust Hub on Jun 29, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the installation of an external CLI tool via
go install github.com/Hyaxia/blogwatcher/cmd/blogwatcher@latest. This downloads source code from a third-party repository and compiles it locally. - [COMMAND_EXECUTION]: The skill uses a local command-line interface (
blogwatcher) to perform its core functions, including adding blogs, scanning feeds, and managing articles. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes content from external RSS and Atom feeds that are not under the user's control.
- Ingestion points: Feed content is retrieved and displayed through the
blogwatcher scanandblogwatcher articlescommands. - Boundary markers: The instructions do not define clear delimiters or use isolation techniques when the agent processes feed data.
- Capability inventory: The skill allows for local command execution and network access to fetch feed updates.
- Sanitization: There is no evidence of content sanitization or validation of the retrieved feed data before it is presented to the agent's context.
Audit Metadata