technical-writing

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection when processing untrusted code or system data for documentation.
  • Ingestion points: Uses Read, Glob, and Grep tools to access source material from the filesystem (documented in SKILL.md).
  • Boundary markers: No explicit delimiters are specified to isolate external content from the agent's core instructions.
  • Capability inventory: Possesses filesystem access through Read, Write, Edit, Glob, and Grep tools.
  • Sanitization: Lacks sanitization or validation of input data to prevent instruction obedience from documented files.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 12:43 PM