skills/clearsmog/claude-skills/review/Gen Agent Trust Hub

review

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core function of reading and processing untrusted file content.
  • Ingestion points: File content from extensions .tex, .qmd, .typ, .py, and .md is read and parsed (SKILL.md).
  • Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the files being reviewed.
  • Capability inventory: The skill utilizes Read, Write, and Task tools to process data and launch sub-agent review processes.
  • Sanitization: There is no evidence of sanitization or filtering of the file content before it is processed by the routing table and sub-agents.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 01:15 AM