self-improving-agent

Pass

Audited by Gen Agent Trust Hub on Jul 18, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill implements an architecture that creates a surface for indirect prompt injection by processing and promoting data from MEMORY.md, which contains untrusted input.
  • Ingestion points: MEMORY.md and topic files are ingested by the memory-analyst agent for pattern recognition.
  • Boundary markers: The skill does not specify the use of boundary markers or delimiters to isolate untrusted content during the analysis or promotion phase.
  • Capability inventory: The skill has the capability to write to and modify project rule files such as CLAUDE.md and .claude/rules/, which directly influence agent behavior.
  • Sanitization: There is no evidence of sanitization, filtering, or validation of the captured memory content before it is promoted to persistent project-level instructions.
  • [COMMAND_EXECUTION]: The installation section provides instructions for executing a local script (./scripts/codex-install.sh) which may perform arbitrary commands on the user's system.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 18, 2026, 04:18 PM
Security Audit — agent-trust-hub — self-improving-agent