help-center-article-generator

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [NO_CODE]: The skill does not contain any executable scripts, binaries, or code-based dependencies. It functions entirely through prompt-based reasoning.\n- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection due to its processing of external, untrusted support data.\n
  • Ingestion points: The skill ingests support ticket exports, FAQ patterns, and existing help articles from URLs or text provided in Phase 0 (SKILL.md).\n
  • Boundary markers: No specific delimiters or safety instructions are provided to the agent to distinguish untrusted data from its core instructions.\n
  • Capability inventory: The skill instructs the agent to write files to the 'clients/' directory on the local file system (SKILL.md).\n
  • Sanitization: No validation or sanitization steps are defined to clean the input data before it is processed and written to disk.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 06:03 PM