grammarly-core-workflow-b

Pass

Audited by Gen Agent Trust Hub on Aug 21, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is designed to ingest and process arbitrary text data through various analysis functions, which presents a surface for indirect prompt injection. If the analyzed text contains malicious instructions, the agent might inadvertently follow them, particularly as it has access to powerful tools like Bash and file system modifications.
  • Ingestion points: Untrusted content enters the workflow via the text parameter in the detectAI, batchAIDetection, and checkPlagiarism functions within SKILL.md.
  • Boundary markers: The instructions do not define delimiters or warnings to ignore embedded instructions within the analyzed text.
  • Capability inventory: The skill allows the agent to use Read, Write, Edit, Bash(npm:*), and Grep tools, which could be abused if an injection is successful.
  • Sanitization: There is no evidence of input validation, escaping, or filtering of the external text content before it is processed.
  • [SAFE]: The skill connects to official Grammarly API domains (api.grammarly.com) and references official documentation (developer.grammarly.com). These are well-known, established services appropriate for the skill's described functionality.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 21, 2026, 06:29 PM
Security Audit — agent-trust-hub — grammarly-core-workflow-b