slfg
Pass
Audited by Gen Agent Trust Hub on Mar 30, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns, exfiltration, or unauthorized commands were detected. The skill is an orchestration script for engineering tasks.
- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it passes user arguments directly to a workflow planner. 1. Ingestion points: $ARGUMENTS in SKILL.md file. 2. Boundary markers: None identified in the instruction set. 3. Capability inventory: Orchestrates tool calls for code planning, execution, and testing. 4. Sanitization: No sanitization logic is present in the skill text.
Audit Metadata