Skills
skills/vishalsachdev/claude-skills/write-article/Gen Agent Trust Hub

write-article

Fail

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: HIGHDATA_EXFILTRATIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [DATA_EXFILTRATION] (HIGH): The skill identifies and reads local session transcript files (~/.claude/projects/.../*.jsonl) and uses the claude-code-transcripts tool with the --gist flag to upload them to GitHub. This exposes private conversation data to an external service.
  • [COMMAND_EXECUTION] (MEDIUM): The skill relies on several local Python scripts located in ~/.claude/skills/write-article/scripts/ (e.g., update-cache.py). Since these scripts are not included in the skill's definition, their behavior regarding file system access and network operations cannot be verified.
  • [EXTERNAL_DOWNLOADS] (MEDIUM): The skill uses uvx claude-code-transcripts to execute code. uvx dynamically downloads and runs packages from external registries (like PyPI), which introduces a supply-chain risk if the package is compromised or malicious.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 17, 2026, 06:42 PM