notion-observability
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of markdown instructions and documentation. It contains no executable scripts, shell commands, or automated installers.
- [SAFE]: External references in
references/official-docs.mdlink exclusively to the official Notion developer portal atdevelopers.notion.com. These are recognized as well-known service references and are documented neutrally. - [INDIRECT_PROMPT_INJECTION]: The skill instructions involve analyzing external documentation and integration code, which constitutes a potential ingestion surface. However, the risk is mitigated by the skill's design:
- Ingestion points: Processes Notion API documentation and repository fixtures (
references/official-docs.md). - Boundary markers: Explicitly defines "Approval Boundaries" and "Tool Discipline" to prevent unauthorized data access.
- Capability inventory: Limited to standard file system tools (
Read,Glob,Grep,Write,Edit); no network or code execution tools are requested. - Sanitization: Mandates redaction before serialization and the use of secret/content canaries to validate that no private data is leaked into observability signals.
Audit Metadata