storyteller-guidance

Pass

Audited by Gen Agent Trust Hub on Jul 25, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is a collection of instructional content and reference markdown files designed to assist users in storytelling. No malicious patterns, obfuscation, or dangerous commands were identified during the analysis.
  • [DATA_EXFILTRATION]: No network operations (such as curl, wget, or fetch) or sensitive file path access (such as .env or SSH keys) were found. The skill operates purely within the text-based context of the conversation.
  • [PROMPT_INJECTION]: The instructions do not contain any patterns typical of prompt injection, such as attempts to bypass safety filters or override the agent's core instructions.
  • [REMOTE_CODE_EXECUTION]: There are no package installations, script executions, or remote code downloads. The skill relies on static reference files located within the references/ directory.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests user descriptions of communication situations to provide coaching. While this is a data ingestion surface, the skill lacks any capabilities (such as writing to the filesystem or making network calls) that could be exploited via indirect injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 25, 2026, 02:27 PM
Security Audit — agent-trust-hub — storyteller-guidance