skills/justyannicc/skills/review/Gen Agent Trust Hub

review

Pass

Audited by Gen Agent Trust Hub on Aug 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is entirely instructional and follows a two-axis review methodology (Standards and Input) without requesting dangerous tools or executing scripts.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data, specifically the 'target' work and 'originating input' documents provided by users.
  • Ingestion points: The agent reads user-supplied targets, work tracker items, and standards documentation as part of the review process.
  • Boundary markers: The instructions mandate 'pinning' the target state to ensure consistency, though they do not explicitly include instructions to ignore embedded commands within the analyzed material.
  • Capability inventory: The skill does not use any subprocess calls, file-writing tools, or network operations, limiting the impact of any potential injection in the processed data.
  • Sanitization: No specific sanitization or filtering of the input content is described.
  • [METADATA_SAFE]: The metadata fields (name, description, homepage) are consistent with the provided functionality and link to the author's official GitHub repository, which is a recognized vendor resource for this skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 16, 2026, 03:24 PM