de-slopify

Pass

Audited by Gen Agent Trust Hub on May 10, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill is focused on code maintenance and follows best practices for a local development tool. It does not involve external downloads, remote code execution, or any form of data exfiltration.
  • [PROMPT_INJECTION]: The skill's functionality involves reading and interpreting code from git branches, creating an indirect prompt injection surface. A malicious actor could craft code or comments designed to trick the agent into removing legitimate security checks or performing unintended modifications during its cleanup process.
  • Ingestion points: Source code diffs from the specified git branch ($1).
  • Boundary markers: None; the agent processes the code content directly without delimiters.
  • Capability inventory: File system write access used to modify or delete code.
  • Sanitization: No sanitization or validation of the branch content is performed before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
May 10, 2026, 07:59 AM
Security Audit — agent-trust-hub — de-slopify