hippocampus

Fail

Audited by Gen Agent Trust Hub on Mar 7, 2026

Risk Level: HIGHCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: Several scripts in the skill are vulnerable to command injection via unsafe string interpolation in Python code blocks.\n
  • Evidence: In scripts/recall.sh, the $QUERY variable is directly concatenated into a Python source string: QUERY = \"$QUERY\".lower(). A maliciously crafted query could escape the string and execute arbitrary Python code. A similar pattern exists in scripts/reinforce.sh using the $MEM_ID variable.\n
  • Impact: This allows for arbitrary code execution within the agent's environment if the agent or a user provides a specially crafted input string.\n- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection due to its processing of untrusted session data.\n
  • Ingestion points: Conversation logs are extracted by preprocess.sh and stored in ~/.openclaw/workspace/memory/signals.jsonl.\n
  • Boundary markers: The instructions for the Hippocampus Agent in agentdir/AGENTS.md and agents/hippocampus-agent.md fail to use delimiters or unique markers to separate the processing instructions from the raw message data.\n
  • Capability inventory: The Hippocampus Agent has the permission to modify the central memory store ~/.openclaw/workspace/memory/index.json using file write operations.\n
  • Sanitization: There is no evidence of sanitization, filtering, or validation of user-provided content before it is presented to the LLM for memory classification.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Mar 7, 2026, 12:01 PM