skills/williacj/claude-skills/grammar/Gen Agent Trust Hub

grammar

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • Indirect Prompt Injection (LOW): The skill is designed to ingest and process arbitrary user text for grammar checking, which is a known vector for indirect prompt injection. While the skill could be instructed by malicious text to ignore its primary task, it possesses no dangerous tools to exploit.\n
  • Ingestion points: User-provided sermons, academic papers, and blog posts processed in Step 3 of the workflow in SKILL.md.\n
  • Boundary markers: Absent; there are no delimiters or specific instructions provided to the agent to treat the user input as data only.\n
  • Capability inventory: No file system access, network requests, or command execution capabilities were detected in any of the skill's files.\n
  • Sanitization: No input validation or sanitization logic is present.\n- No Executable Code (SAFE): The skill consists entirely of Markdown files for instructions and style references, with no Python scripts, Node.js packages, or binary executables detected.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:22 PM