live-web-page-browser
Pass
Audited by Gen Agent Trust Hub on Jul 28, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill documentation refers to installation commands that download content from the vendor's official GitHub repository.
- Evidence:
npx skills add AgentPMT/agent-skills --skill what-is-agentpmtas documented inSKILL.md. - [PROMPT_INJECTION]: The skill facilitates the ingestion of untrusted data from external websites, creating a surface for indirect prompt injection.
- Ingestion points: Web content retrieval actions such as
get_url_html_content,get_url_markdown, andget_url_snapshotdefined inSKILL.md. - Boundary markers: Absent. The skill does not provide instructions for the agent to use delimiters or ignore instructions embedded within the fetched content.
- Capability inventory: The skill enables network retrieval of external data but does not include local file system write access or arbitrary command execution.
- Sanitization: No evidence of automated sanitization or filtering of retrieved web content is provided in the skill instructions.
Audit Metadata