basic-memory-workflow

Pass

Audited by Gen Agent Trust Hub on Mar 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONNO_CODE
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides instructions for the agent to use the 'basic-memory' CLI tool to perform search, read, and write operations on local project files.
  • [PROMPT_INJECTION]: The skill defines a surface for indirect prompt injection as it ingests untrusted data from local notes and provides the agent with command execution capabilities. Ingestion points: read-note and search-notes in SKILL.md. Boundary markers: Absent. Capability inventory: basic-memory tool execution in SKILL.md. Sanitization: Absent.
  • [NO_CODE]: No scripts or executable files are included; the skill consists entirely of instructional markdown.
  • [SAFE]: No malicious patterns or data exfiltration attempts were identified. The skill correctly instructs the agent to avoid storing sensitive data.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 17, 2026, 04:55 PM