memory-discipline

Pass

Audited by Gen Agent Trust Hub on Aug 15, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow that utilizes memory_smart_search to retrieve data from a persistent store, creating a potential surface for indirect prompt injection where instructions stored in previous sessions could influence current agent behavior.\n
  • Ingestion points: Data retrieved via the memory_smart_search tool as described in SKILL.md.\n
  • Boundary markers: The instructions do not include specific delimiters or guidelines to ignore embedded instructions within the retrieved memory content.\n
  • Capability inventory: The skill utilizes memory_smart_search for reading and memory_save for writing to a persistent memory store.\n
  • Sanitization: There is no mention of sanitizing or validating the content retrieved from memory before it is processed by the agent.\n- [NO_CODE]: This skill consists entirely of instructional markdown and does not include any executable scripts, binaries, or automated configuration files.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 15, 2026, 11:27 PM
Security Audit — agent-trust-hub — memory-discipline