skills/openclaw/skills/News/Gen Agent Trust Hub

News

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is designed to process and summarize external news content, creating a surface for indirect prompt injection where malicious instructions could be embedded in news articles.\n
  • Ingestion points: Processes external news articles and briefings fetched from sources specified in the user's local memory or via external scraping tools as defined in the Core Rules of SKILL.md.\n
  • Boundary markers: The skill lacks explicit instructions to wrap external content in delimiters or to disregard embedded instructions within the ingested news data.\n
  • Capability inventory: The skill is authorized to read and write profile, history, and source information within the user's ~/news/ directory.\n
  • Sanitization: No specific sanitization, filtering, or validation of the ingested news content is specified in the instruction set.\n- [NO_CODE]: The skill consists exclusively of markdown instructions and metadata. It does not contain any scripts, binaries, or direct shell command execution logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 02:43 AM