opener-variator

Pass

Audited by Gen Agent Trust Hub on Mar 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides automated text-editing functionality for local markdown subsections. No malicious patterns or security risks were identified within the workflow or instructions.- [SAFE]: The skill operates locally on files within the project structure (e.g., sections/*.md) and specifically states 'Network: none' in its configuration.- [PROMPT_INJECTION]: Analysis of the indirect prompt injection surface identifies that while the skill processes external content, the risk is negligible due to the narrow scope of rewriting and strong role constraints.
  • Ingestion points: Reads from sections/S<sub_id>.md and output/WRITER_SELFLOOP_TODO.md.
  • Boundary markers: Not explicitly used, but processing is restricted to the first paragraph.
  • Capability inventory: Restricted to reading and writing local text files.
  • Sanitization: Not applicable as it is a text-editing utility.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 15, 2026, 02:00 PM