gsp-compare-backends
Pass
Audited by Gen Agent Trust Hub on May 3, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by processing untrusted user inputs (backend options) and persisting them to a local file.
- Ingestion points: User-provided backend profile options and comparison criteria (SKILL.md).
- Boundary markers: Absent; there are no instructions to delimit or ignore instructions within the input data.
- Capability inventory: File write operations to
docs/game-studio/backend-decision.md. - Sanitization: Absent; the skill does not specify validation or escaping for the comparison results before writing.
Audit Metadata