recent-news-article-aggregator
Pass
Audited by Gen Agent Trust Hub on Jun 24, 2026
Risk Level: SAFENO_CODEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill contains no executable scripts or local code files. It defines functionality through markdown instructions for remote tool calls and JSON schemas.
- [EXTERNAL_DOWNLOADS]: The skill documentation provides commands for installing related setup skills from the vendor's official repository (AgentPMT/agent-skills) using package managers like npx and openclaw.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it retrieves and processes headlines and snippets from various external news sources.
- Ingestion points: News article titles, descriptions, and snippets retrieved via the search action (File: SKILL.md).
- Boundary markers: The skill does not instruct the agent to use delimiters or include warnings to ignore instructions found within the article data.
- Capability inventory: The skill facilitates API-based searches but does not have access to sensitive local files or the ability to execute system commands.
- Sanitization: There are no documented procedures for sanitizing or filtering the content of retrieved articles to remove potential malicious instructions.
Audit Metadata