panews-web-viewer
Pass
Audited by Gen Agent Trust Hub on Mar 26, 2026
Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: The
scripts/fetch-page.mjsscript accepts arbitrary URLs starting withhttporhttpsand returns the response content. This behavior can be exploited for Server-Side Request Forgery (SSRF) or to exfiltrate data to an attacker-controlled server if the agent environment has access to internal services or local sensitive files that can be appended to a URL. - [PROMPT_INJECTION]: The skill creates an indirect prompt injection surface by retrieving and processing external website content as Markdown.
- Ingestion points:
scripts/fetch-page.mjsfetches content fromwww.panewslab.comor any URL provided as a command-line argument. - Boundary markers: No boundary markers or 'ignore' instructions are used to separate fetched content from the agent's core instructions.
- Capability inventory: The script uses the Node.js
fetchAPI to retrieve and print network data to stdout. - Sanitization: There is no evidence of content sanitization or validation of the Markdown data retrieved from the remote source.
Audit Metadata