javascript-surface-analyzer
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted JavaScript and HTML content from user-provided URLs, creating a vulnerability surface for indirect prompt injection.
- Ingestion points: The agent ingests data from external scripts and pages specified by
target_urlandseed_pagesinSKILL.md. - Boundary markers: The instructions do not provide delimiters or 'ignore' markers to help the agent distinguish between its core security task and potentially malicious instructions embedded in the analyzed code (e.g., in comments or strings).
- Capability inventory: To perform its tasks, the agent likely utilizes network access (to fetch scripts) and output generation (to report findings), which could be subverted if an injection is successful.
- Sanitization: There are no instructions to sanitize or escape the content being analyzed before it enters the agent's context window, allowing raw, untrusted strings to influence the agent's behavior.
Audit Metadata