people-memory
Pass
Audited by Gen Agent Trust Hub on Jun 20, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [SAFE]: No malicious behavior or patterns were detected in the skill instructions or companion files. The skill adheres to its stated purpose of managing contact data in an Obsidian vault.- [COMMAND_EXECUTION]: The skill uses file operations to search, read, and update markdown files within a specific vault subdirectory ('06
- People/'). These actions are necessary for the skill's functionality and are appropriately scoped.- [INDIRECT_PROMPT_INJECTION]: The skill exhibits a potential surface for indirect prompt injection as it persists conversation data to files. Ingestion points: Information about people provided by the user in chat (SKILL.md). Boundary markers: The skill uses Markdown headers and YAML frontmatter to delimit data (TEMPLATES.md). Capability inventory: Search, read, and write operations are performed on local files (REFERENCE.md). Sanitization: The skill performs name normalization and ensures YAML frontmatter remains valid (QA.md).
Audit Metadata