external-system-debugging
Pass
Audited by Gen Agent Trust Hub on Jul 31, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it guides the agent to ingest and analyze data from untrusted external sources without adequate safety boundaries.\n
- Ingestion points: Data enters the agent's context through
navigator.clipboard.read()output,el.outerHTMLDOM captures, and HTTP response data collected viacurlas described inSKILL.mdandreferences/template-browser-paste-format.md.\n - Boundary markers: The skill does not instruct the agent to use delimiters or 'ignore embedded instructions' markers when processing the gathered external data.\n
- Capability inventory: The skill enables the agent to recommend and analyze the output of shell commands (e.g.,
curl,pbpaste) and perform DOM manipulations.\n - Sanitization: While the skill suggests avoiding
innerHTMLin implementation to prevent XSS, it lacks instructions for sanitizing or validating external content before the agent interprets it.
Audit Metadata