skills/adobe/skills/docs-search/Gen Agent Trust Hub

docs-search

Pass

Audited by Gen Agent Trust Hub on May 22, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches documentation indexes (docpages-index.json and query-index.json) from www.aem.live, which is an official Adobe domain associated with AEM Edge Delivery Services.
  • [COMMAND_EXECUTION]: Executes a local utility script scripts/search.js using Node.js to filter documentation based on user-provided keywords.
  • [PROMPT_INJECTION]: The skill processes data from an external source (documentation pages), which represents an indirect prompt injection surface. This is a characteristic of search-based skills.
  • Ingestion points: The script fetches JSON indexes from the network; the instructions direct the agent to fetch full documentation content from the vendor's site.
  • Boundary markers: The skill does not explicitly define delimiters for the external content in its instructions.
  • Capability inventory: The skill is capable of network GET requests and local file writes for caching documentation metadata.
  • Sanitization: Documentation content is processed as-is from the vendor's official documentation source.
Audit Metadata
Risk Level
SAFE
Analyzed
May 22, 2026, 05:05 AM
Security Audit — agent-trust-hub — docs-search