desloppify

Pass

Audited by Gen Agent Trust Hub on Jul 27, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The script scripts/desloppify_portable.py executes git and desloppify binaries using subprocess.run and os.execvpe. These commands are used for local repository inspection and running the maintainability analysis engine on the project root specified by the user.
  • [PROMPT_INJECTION]: The SKILL.md instructions include proactive security guidance, specifically directing the agent to treat repository comments and text as untrusted data rather than instructions, which mitigates indirect prompt injection risks.
  • [EXTERNAL_DOWNLOADS]: The skill documentation provides instructions for the user to manually install the required desloppify engine from the official repository or package registry using uv. The skill itself does not perform automatic or hidden network downloads.
  • [DATA_EXFILTRATION]: The Python script detects the execution environment (harness) by checking for the presence of specific environment variables (e.g., CLAUDE_CODE_SESSION_ID, CODEX_THREAD_ID). This data is used solely for local configuration and is not transmitted externally.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 27, 2026, 03:12 AM
Security Audit — agent-trust-hub — desloppify