skills/ivcota/skills/writing-style/Gen Agent Trust Hub

writing-style

Pass

Audited by Gen Agent Trust Hub on Mar 25, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted text samples, creating an indirect prompt injection surface.
  • Ingestion points: User-provided text samples or files matching ./blog-posts/*.md (SKILL.md).
  • Boundary markers: Absent; there are no instructions to the agent to ignore potentially malicious commands within the samples.
  • Capability inventory: The skill performs file read and write operations on STYLE_PROFILE.md (SKILL.md).
  • Sanitization: Absent; the skill analyzes and extracts excerpts directly from provided content.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 25, 2026, 09:42 PM