skills/narumiruna/skills/memory-md/Gen Agent Trust Hub

memory-md

Pass

Audited by Gen Agent Trust Hub on May 17, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill processes content from a local file (MEMORY.md), which serves as an indirect prompt injection surface if the file is modified by untrusted contributors in a shared repository environment. \n
  • Ingestion points: Instructions in SKILL.md direct the agent to read MEMORY.md for project context at the start of conversations. \n
  • Boundary markers: No specific delimiters or safety wrappers are defined to separate the file content from system instructions. \n
  • Capability inventory: The skill is intended to perform read and write operations on local repository files. \n
  • Sanitization: No content validation or sanitization process is specified for the data read from the file beyond conforming to specified bullet point patterns.
Audit Metadata
Risk Level
SAFE
Analyzed
May 17, 2026, 10:02 AM
Security Audit — agent-trust-hub — memory-md