electron
Pass
Audited by Gen Agent Trust Hub on Apr 18, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it reads and processes data from external applications (e.g., Slack, Discord, VS Code) that contain untrusted content from third parties.
- Ingestion points: Data is ingested through
agent-browser snapshotandagent-browser get textas seen inSKILL.md. - Boundary markers: The skill lacks explicit delimiters or instructions to treat ingested app content as data rather than instructions.
- Capability inventory: The skill uses
agent-browserto perform actions like clicking, typing, and navigating within the application, which could be manipulated by malicious content within the app (e.g., a Slack message instructing the agent to perform an action). - Sanitization: No sanitization or validation mechanisms are described for the content extracted from target applications.
Audit Metadata