paniolo-file-splitting
Pass
Audited by Gen Agent Trust Hub on Jul 21, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection due to its core function of ingesting and refactoring untrusted source code files.
- Ingestion points: The agent reads consolidated source files to identify symbols, JSDoc, and imports as specified in the SKILL.md preconditions and evaluations.
- Boundary markers: Absent. The skill provides no instructions for the agent to use delimiters or to ignore natural language instructions that might be embedded within the code, comments, or strings of the target files.
- Capability inventory: The skill has significant capabilities including reading and writing files, deleting files (removing the original consolidated file), and executing terminal commands such as 'git grep', 'npm run lint', and 'npm run test:unit'.
- Sanitization: Absent. There is no requirement or mechanism described to sanitize, escape, or validate the content of the source files before they are processed by the agent.
Audit Metadata