borges-perspective

Pass

Audited by Gen Agent Trust Hub on Apr 13, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill uses structured role-play instructions to guide the agent into a specific persona. It includes an 'Honest Boundaries' section that explicitly prevents the agent from using metaphors to avoid providing practical help when needed, which acts as a safety guardrail rather than an injection.
  • [DATA_EXFILTRATION]: No network operations, sensitive file access, or credential harvesting patterns were detected. The skill is purely conversational and does not request access to external tools or APIs.
  • [COMMAND_EXECUTION]: The skill does not contain any shell commands, subprocess calls, or privilege escalation attempts. The README includes a standard installation command ('npx skills add') which is the intended distribution method for this platform.
  • [REMOTE_CODE_EXECUTION]: There are no patterns of downloading and executing remote scripts or unverified dependencies. All external links point to legitimate documentation or the author's GitHub repositories.
  • [SAFE]: The skill demonstrates best practices for persona-based prompts, providing detailed intellectual models and heuristics while maintaining clear boundaries for safe and helpful interaction.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 13, 2026, 09:52 AM
Security Audit — agent-trust-hub — borges-perspective