conversation-memory

Pass

Audited by Gen Agent Trust Hub on Aug 9, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill logic for entity extraction presents an indirect prompt injection vulnerability. Untrusted user input is directly included in prompts used for memory storage operations.\n
  • Ingestion points: The extractAndStore and addMessage methods in SKILL.md ingest untrusted content from the message.content field.\n
  • Boundary markers: The prompt template used for entity extraction lacks delimiters or instructions to the LLM to treat interpolated content as data rather than instructions.\n
  • Capability inventory: The code demonstrates persistent storage, search, and structured output parsing, but does not include high-risk capabilities like shell access or network requests to untrusted domains.\n
  • Sanitization: No validation or escaping is applied to the user-supplied content before it is stored or used in prompt generation.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 9, 2026, 04:04 PM
Security Audit — agent-trust-hub — conversation-memory