summarize

Pass

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is purely instructional and guides the agent on how to organize and condense conversation history into a structured briefing. It does not include scripts, binaries, or commands that interact with the host system.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process conversation history, which is untrusted data that could contain malicious instructions. However, since the skill only produces a text summary and does not invoke external tools or perform high-risk actions, the impact of such an injection is minimal.
  • Ingestion points: Full conversation history (analyzed in Step 1).
  • Boundary markers: Absent; the instructions do not specify delimiters for separating user content from instructions.
  • Capability inventory: None; the skill generates text output for the user and does not use file-system or network tools.
  • Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 02:25 PM
Security Audit — agent-trust-hub — summarize