project-standards

Pass

Audited by Gen Agent Trust Hub on Mar 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection as it processes various files from the repository to infer standards.
  • Ingestion points: Per SKILL.md, the skill reads configuration files (ESLint, Prettier, TypeScript), test files, and source code.
  • Boundary markers (present): SKILL.md includes instructions to treat all scanned content strictly as data and to ignore instructions within them.
  • Capability inventory: SKILL.md defines usage of Read, Write, Edit, Glob, and Grep tools, allowing modifications to documentation files.
  • Sanitization (present): SKILL.md requires sanitizing extracted content to remove malicious markdown or HTML tags.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 18, 2026, 08:10 AM