deslop
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill identifies an attack surface for indirect prompt injection because it processes external data (git diffs) which could contain adversarial instructions. Ingestion points: Code diff against main in SKILL.md. Boundary markers: Absent; the agent is not instructed to treat the code solely as data. Capability inventory: File modification via removal and change operations in SKILL.md. Sanitization: Absent; no validation or filtering of the code diff is performed.
Audit Metadata