people-crm
Pass
Audited by Gen Agent Trust Hub on Aug 3, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or security vulnerabilities were identified in the skill instructions, scripts, or metadata.- [INDIRECT_PROMPT_INJECTION]: The skill processes user-created Markdown notes which constitutes a potential attack surface for indirect prompt injection.
- Ingestion points: Markdown files located in the
People/,Organizations/, andProjects/directories. - Boundary markers: The skill uses standard YAML frontmatter delimiters (
---) to structure entity data. - Capability inventory: The skill's operations are limited to reading and writing Markdown files; it does not utilize tools for network access, shell execution, or privilege escalation.
- Sanitization: No explicit sanitization or input validation for note content is described, but the risk is mitigated by the lack of high-privilege capabilities.
Audit Metadata