notion
Pass
Audited by Gen Agent Trust Hub on Apr 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses shell commands such as
curlto interact with the Notion API andcatto retrieve a locally stored API key. - [DATA_EXFILTRATION]: The skill accesses a sensitive credential file at
~/.config/notion/api_keyand transmits the token to Notion's official API domain (api.notion.com). This behavior is required for the skill's stated functionality. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from an external source.
- Ingestion points: External data enters the context through
GETrequests to the Notion API (api.notion.com) described inSKILL.md. - Boundary markers: The skill does not employ delimiters or specific instructions to the agent to ignore potentially malicious content within the retrieved Notion data.
- Capability inventory: The skill utilizes shell command execution (
curl) for network operations and file access. - Sanitization: There is no evidence of sanitization or validation of the content retrieved from Notion before it is processed by the agent.
Audit Metadata