docs-applies-to-tagging

Pass

Audited by Gen Agent Trust Hub on May 26, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches documentation syntax, guidelines, and key references from official vendor domains including elastic.github.io and elastic.co to ensure validation accuracy.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes content from external documentation files.
  • Ingestion points: Discovers files using the Glob tool and ingests their content into the agent's context via the Read tool.
  • Boundary markers: The instructions do not define specific delimiters or instructions to prevent the agent from obeying instructions potentially embedded within the documentation being processed.
  • Capability inventory: The skill has access to file system tools for reading and writing (Read, Glob, Edit) and network access via WebFetch.
  • Sanitization: There are no documented procedures for sanitizing or filtering file content for malicious prompts before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
May 26, 2026, 07:10 AM
Security Audit — agent-trust-hub — docs-applies-to-tagging