news-aggregator-skill
Fail
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: CRITICALINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill fetches and analyzes content from untrusted external sources, such as news articles and social media posts. This creates a surface for indirect prompt injection, where malicious instructions hidden in the fetched content could be interpreted and executed by the agent.
- Ingestion points: External article text is fetched and extracted by
scripts/fetch_news.pythrough thefetch_url_contentfunction. - Boundary markers: The
SKILL.mdinstructions lack clear delimiters or warnings to the agent to disregard instructions found within the aggregated news data. - Capability inventory: The agent can perform network operations via the fetcher script and write output files to the
reports/directory. - Sanitization: No content sanitization is performed beyond basic HTML tag removal.
- [EXTERNAL_DOWNLOADS]: The skill interacts with numerous external domains to aggregate data. Automated scanners flagged a malicious URL (
Genstore.ai) in one of the included sample reports (reports/ai_hot_20260205_1432.md), demonstrating that the skill's data aggregation process can ingest and propagate links to blacklisted or dangerous websites.
Recommendations
- CRITICAL: 1 file(s) identified as malware by FileRep - DO NOT USE
- Contains 1 malicious URL(s) - DO NOT USE
Audit Metadata