context-compactor

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection (LOW): The skill processes untrusted message context through summarization and extraction logic, which can be a surface for indirect prompt injection. \n
  • Ingestion points: Untrusted data enters the agent context through the compact method in scripts/compactor.py and various summarization functions in scripts/summarizer.py. \n
  • Boundary markers: Compaction results are identified by a [SUMMARIZED CONTEXT] header, but individual summarized data points lack isolation markers to prevent instruction following. \n
  • Capability inventory: No dangerous system-level capabilities (e.g., shell execution, network requests, or file writing) were identified within the provided scripts. \n
  • Sanitization: No explicit sanitization or filtering is performed on the content before summarization. The extraction logic in scripts/importance_scorer.py specifically searches for decision-related keywords, which an attacker could use to ensure their malicious instructions are preserved and prioritized.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:11 PM