memmy-memory

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill instructs the agent to use --token <token> via CLI parameters, which can lead to passing bearer tokens directly as command-line arguments and exposing secrets in the LLM's output.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). The agent skill interfaces with a memory service where stored memories (retrieved via search or turn start) can originate from past user interactions or untrusted entries, exposing the agent to indirect prompt injection via recalled memory content.