intl-news-report

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill exposes a surface for indirect prompt injection by processing external web content.
  • Ingestion points: Data is ingested via google_web_search and newscli tools as specified in SKILL.md.
  • Boundary markers: Absent. The skill does not instruct the agent to use delimiters or specifically ignore instructions found within the fetched news data.
  • Capability inventory: Functionality is limited to text synthesis and reporting; the skill does not have access to file-system operations, sensitive network calls, or command execution.
  • Sanitization: Absent. External content is curated into a structured report without specific filtering or validation steps.
  • [NO_CODE]: The skill consists entirely of markdown-based instructions and does not include any executable scripts, binaries, or configuration files that could hide malicious logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 04:19 PM