burner-agents-privacy
Warn
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to clone a repository from
https://github.com/NotPBShaw/burner-agents.gitand install theburner-agentspackage. These sources are not from verified or trusted organizations, which may lead to the execution of unvetted code within the environment. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data by browsing and analyzing live web pages using an LLM reasoning engine.
- Ingestion points: Web page content is retrieved and processed by the agent in the reasoning engine methods shown in
SKILL.md. - Boundary markers: No explicit markers or instructions are provided to distinguish between user intent and instructions that may be embedded in the processed web content.
- Capability inventory: The agent can perform interactive browser operations, such as clicking and navigating, as described in
SKILL.md. - Sanitization: The skill does not implement sanitization or filtering of the web content before it is processed by the reasoning engine.
Audit Metadata