news-discover
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted data from external web search results.
- Ingestion points: News content retrieved via web search (referenced in Step 1 of the Workflow in
SKILL.md). - Boundary markers: None. The skill does not define clear delimiters or instructions to ignore potential injections within the fetched news text.
- Capability inventory: None. The skill does not include scripts or executable tools that could be exploited by an injection.
- Sanitization: None. There is no mention of filtering or validating the content of the news stories before summarization.
Audit Metadata