skills/huntsyea/hstack/human-writing/Gen Agent Trust Hub

human-writing

Pass

Audited by Gen Agent Trust Hub on Sep 1, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted user-supplied text for editing and analysis. While this serves as a potential vector for indirect prompt injection, the risk is mitigated as the skill has no access to sensitive tools or system commands.
  • Ingestion points: User-provided drafts are ingested via the 'Edit', 'Detect', and 'Technical documentation' modes described in SKILL.md.
  • Boundary markers: The instructions do not define specific boundary markers for user-provided content.
  • Capability inventory: The skill uses no tools, network operations, or file system permissions.
  • Sanitization: No input sanitization is performed, which is standard for a text-based editing assistant with limited capabilities.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 1, 2026, 01:21 AM
Security Audit — agent-trust-hub — human-writing