news-monitor
Pass
Audited by Gen Agent Trust Hub on Jun 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
uvxto execute theweb-foragerpackage anduv runto execute a Python script utilizing theddgslibrary. These commands are used to perform news searches as part of the skill's primary function. - [EXTERNAL_DOWNLOADS]: The skill fetches article content from external websites via the
r.jina.aimarkdown conversion service usingcurl. Jina AI is a well-known service for this purpose. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it retrieves and processes untrusted content from the web.
- Ingestion points: News article snippets and full text content retrieved from external URLs (SKILL.md).
- Boundary markers: No explicit markers are used to delimit external content from the prompt instructions.
- Capability inventory: Subprocess execution via
uvx,uv run, andcurlfor searching and fetching content (SKILL.md). - Sanitization: No content validation or escaping is specified before the AI processes the data.
Audit Metadata