memory-recall

Pass

Audited by Gen Agent Trust Hub on Jul 27, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructions utilize shell commands (mi cortex recall "") that interpolate user-provided input. This pattern is vulnerable to command injection if the agent fails to sanitize shell metacharacters in the query string.- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from a vector database and returns it to the agent context.
  • Ingestion points: Content excerpts returned by the mi cortex recall command described in SKILL.md.
  • Boundary markers: None. The skill does not define explicit delimiters or include instructions for the agent to ignore embedded commands within the search results.
  • Capability inventory: Shell command execution via the mi CLI tool for searching and retrieving document content.
  • Sanitization: None. The skill does not specify any filtering or sanitization of the retrieved memory excerpts before they are processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 27, 2026, 06:18 AM
Security Audit — agent-trust-hub — memory-recall