blogwatcher
Pass
Audited by Gen Agent Trust Hub on Apr 25, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches pre-compiled binaries and installation components from the author's official GitHub repository (github.com/JulienTant/blogwatcher-cli).
- [COMMAND_EXECUTION]: Executes the blogwatcher-cli command-line tool to manage blog subscriptions, scan for updates, and scrape article content.
- [DATA_EXFILTRATION]: Performs network operations to fetch RSS/Atom feeds and blog HTML content from arbitrary third-party domains.
- [PROMPT_INJECTION]: Indirect prompt injection surface detected through the processing of untrusted external data. 1. Ingestion points: External RSS/Atom feeds, HTML scraping of blogs, and imported OPML files. 2. Boundary markers: Absent; the instructions do not define delimiters to distinguish between untrusted feed content and agent instructions. 3. Capability inventory: Uses the blogwatcher-cli tool for local database management and network requests. 4. Sanitization: No explicit sanitization or filtering logic is specified for the processed content within the skill instructions.
Audit Metadata