record-memory

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute various subcommands of the doctrine CLI tool, such as record, link, edit, verify, and find, to manage project-specific knowledge stored in the .doctrine/memory/items/ directory.
  • [INDIRECT_PROMPT_INJECTION]: The skill involves scanning local files like notes.md, phase sheets, and audit findings to extract durable guidance. This data ingestion represents a potential surface for indirect prompt injection if those files contain untrusted content.
  • Ingestion points: Reads from notes.md, active runtime phase sheets, audit findings, and fresh gotchas.
  • Boundary markers: None specified; the skill does not explicitly instruct the agent to use delimiters when processing or recording this content.
  • Capability inventory: The skill uses the doctrine CLI tool for data persistence and retrieval.
  • Sanitization: No validation or sanitization steps are mentioned for the content extracted from the source files.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 04:30 AM
Security Audit — agent-trust-hub — record-memory