Skills
Navigate
skills/jeremylongshore/tons-of-skills-marketplace/grammarly-core-workflow-b/Gen Agent Trust Hub

grammarly-core-workflow-b

Pass

Audited by Gen Agent Trust Hub on Sep 3, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted text data for AI and plagiarism analysis.
  • Ingestion points: The text parameter in the detectAI, batchAIDetection, and checkPlagiarism functions in SKILL.md.
  • Boundary markers: None. The skill does not use delimiters to isolate user content from the prompt context.
  • Capability inventory: The skill uses fetch for network operations and has access to file system tools (Read, Write, Edit).
  • Sanitization: There is no evidence of semantic sanitization or filtering of the input text before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 3, 2026, 10:33 AM