ft-remove-ai-code-slop

Pass

Audited by Gen Agent Trust Hub on May 13, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes untrusted data from git diffs that could contain malicious instructions.
  • Ingestion points: Git branch diffs (referenced in SKILL.md).
  • Boundary markers: Absent. There are no specific delimiters or instructions to ignore prompts embedded within the diff content.
  • Capability inventory: File system write access to modify code within the repository.
  • Sanitization: Absent. No sanitization or validation of the diff data is performed before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
May 13, 2026, 02:06 PM