create-task
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns, hidden commands, or credentials were found. The skill is entirely instructional.
- [NO_CODE]: The skill does not include any scripts, binaries, or automated executable components.
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to process user-supplied task details to populate Notion database rows, which is a common surface for indirect prompt injection.
- Ingestion points: User-provided task title and optional metadata (SKILL.md).
- Boundary markers: None explicitly mentioned for user input.
- Capability inventory: Notion MCP server interaction for database creation; no local script execution or network operations identified.
- Sanitization: None defined in the skill logic.
Audit Metadata