every-style-editor

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [NO_CODE] (SAFE): The skill consists exclusively of markdown instructions for the AI and contains no scripts, binaries, or package dependencies.
  • [PROMPT_INJECTION] (SAFE): No malicious patterns designed to override agent behavior or bypass safety filters were detected.
  • [DATA_EXFILTRATION] (SAFE): There are no indicators of network activity, credential handling, or access to sensitive system files.
  • [INDIRECT_PROMPT_INJECTION] (SAFE): The skill is designed to process external user text, but the lack of executable capabilities (e.g., shell access, file writing, or internet access) mitigates any risk. Evidence: Ingestion points: User-provided text for editing (SKILL.md); Boundary markers: Absent; Capability inventory: None; Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:01 PM