skills/htlin222/dotfiles/prisma-check/Gen Agent Trust Hub

prisma-check

Pass

Audited by Gen Agent Trust Hub on Feb 23, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [NO_CODE] (SAFE): This skill consists entirely of markdown instructions and contains no executable code, Python scripts, or Node.js packages.\n- [SAFE] (SAFE): No malicious patterns such as prompt injection, obfuscation, or persistence mechanisms were detected. The skill purely guides the AI's reasoning for manuscript auditing.\n- [Indirect Prompt Injection] (SAFE): While the skill processes untrusted manuscript data, it is rated as safe.\n
  • Ingestion points: User-provided manuscripts defined in workflow step 1 of SKILL.md.\n
  • Boundary markers: Absent in the workflow instructions.\n
  • Capability inventory: No subprocess calls, network operations, or file-write capabilities across the skill definition.\n
  • Sanitization: Absent. The lack of dangerous capabilities mitigates the risk of processing untrusted content.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 23, 2026, 03:32 AM