keyboard-gremlin
Pass
Audited by Gen Agent Trust Hub on Jun 28, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill's instructions are confined to improving the accuracy and focus of code edits. There are no indications of data exfiltration, unauthorized network requests, or credential theft.
- [PROMPT_INJECTION]: The skill reads and modifies local source code, which introduces a surface for indirect prompt injection where instructions embedded in the code could influence the agent. 1. Ingestion points: Local source code files (SKILL.md). 2. Boundary markers: None present. 3. Capability inventory: File reading and editing (SKILL.md). 4. Sanitization: None present.
Audit Metadata