para-memory-files

Pass

Audited by Gen Agent Trust Hub on Apr 8, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute the 'qmd' command-line tool for indexing and performing semantic searches on files located within the agent's home directory.
  • [PROMPT_INJECTION]: The skill implements a long-term memory system that creates a surface for indirect prompt injection by ingesting untrusted data from user conversations into persistent storage.
  • Ingestion points: Conversation logs and extracted facts are stored in '$AGENT_HOME/memory/' and '$AGENT_HOME/life/' respectively, as described in 'SKILL.md'.
  • Boundary markers: The instructions do not specify the use of delimiters or safety warnings when the agent retrieves and processes these stored memories in future sessions.
  • Capability inventory: The skill performs file read/write operations and executes shell commands ('qmd') to manage the memory system.
  • Sanitization: There is no evidence of sanitization, validation, or filtering of the content stored in or retrieved from the memory files.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 8, 2026, 02:29 PM
Security Audit — agent-trust-hub — para-memory-files