pushbullet
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
@useclawlink/clitool throughnpxto perform authentication (login), service connection (connect), and action execution (run). These operations are standard for a CLI-driven integration and align with the skill's stated purpose. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to read data from Pushbullet, which serves as an external data ingestion surface. To mitigate potential risks from processing untrusted external content, the instructions explicitly mandate that the agent must read the data first and request explicit user confirmation before executing any write operations.
Audit Metadata