typo3-simplify
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill identifies and processes local source code files via git commands, which represents a potential ingestion point for malicious instructions hidden within code comments or data.
- Ingestion points: Source code files identified in the Process section of SKILL.md (e.g., via git diff).
- Boundary markers: Absent; the instructions do not require the agent to wrap external code in delimiters or use explicit prompts to ignore embedded instructions.
- Capability inventory: The skill is used in a context where the agent reads local files and suggests or applies code modifications (writes).
- Sanitization: Absent; no validation or sanitization is performed on the ingested code to prevent embedded natural language commands from affecting the agent's logic.
Audit Metadata