summarize

Pass

Audited by Gen Agent Trust Hub on Jul 8, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill's documentation provides an installation command 'npx clawhub@latest install summarize' which retrieves the skill from an external registry.- [PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from diverse external sources, creating a surface for indirect prompt injection where malicious instructions in the input could influence the agent's behavior.
  • Ingestion points: Web content via 'web_fetch', local and remote office documents (PDF, DOCX, XLSX, PPTX), email threads, and social media posts.
  • Boundary markers: The skill logic does not specify the use of delimiters or 'ignore' instructions to isolate untrusted content from the agent's core instructions.
  • Capability inventory: The skill utilizes tools like 'web_fetch', 'read', and 'tavily-search' to access data across the network and local system.
  • Sanitization: While 'PII desensitization' is mentioned as a best practice, no specific technical mechanisms are defined to sanitize or escape potentially malicious instructions within the text being summarized.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 8, 2026, 04:47 PM
Security Audit — agent-trust-hub — summarize