every-style-editor

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE] (SAFE): No malicious patterns, obfuscation, or security bypass attempts were detected. The skill is limited to providing text-based feedback on grammar and style.
  • [INDIRECT_PROMPT_INJECTION] (SAFE): Ingestion points: Processes user-provided copy for editorial review (SKILL.md). Boundary markers: Absent; no specific delimiters are defined for user text. Capability inventory: The skill is restricted to generating text summaries and line-by-line corrections; it has no file-write, network, or subprocess capabilities. Sanitization: Absent. Assessment: Although the skill ingests untrusted user content, it lacks any dangerous capabilities that could be exploited via indirect injection, and the ingestion is required for its primary editorial function.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:50 PM