emotional-arc-designer

Pass

Audited by Gen Agent Trust Hub on Sep 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill consists entirely of instructional markdown content and does not invoke any system commands, file operations, or network requests.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data, creating a potential surface for indirect prompt injection. * Ingestion points: Data entering the context includes 'Target Human' profiles and 'Objective' shift descriptions (referenced in SKILL.md). * Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands within the input data. * Capability inventory: The skill does not possess any capabilities for subprocess calls, file-writing, or network operations across any included instructions. * Sanitization: No sanitization or input validation logic is present for the ingested data.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 6, 2026, 02:23 PM
Security Audit — agent-trust-hub — emotional-arc-designer