skills/mitodl/agent-kit/agent-memory/Gen Agent Trust Hub

agent-memory

Pass

Audited by Gen Agent Trust Hub on Jun 22, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill creates an indirect prompt injection surface by instructing the agent to read and follow project facts and patterns from a shared external memory graph.
  • Ingestion points: Data enters the agent's context through the memory_get_project_facts, memory_list_patterns, and memory_search functions defined in SKILL.md.
  • Boundary markers: There are no instructions providing delimiters or 'ignore embedded instructions' warnings for the data retrieved from the witan MCP server.
  • Capability inventory: While the skill does not explicitly call dangerous system commands, the instructions suggest that the data retrieved should influence code implementation, library choice, and deployment decisions.
  • Sanitization: No sanitization or content validation steps are documented for the ingested memory data.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 22, 2026, 01:44 PM
Security Audit — agent-trust-hub — agent-memory