typescript-refactorer
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data in the form of TypeScript source files and a configuration file (
config/defaults.md).\n - Ingestion points: The skill instructions in
SKILL.mddirect the agent to "Scan the specified files" and read a configuration file (config/defaults.md) provided in the user's environment.\n - Boundary markers: The skill does not define any specific delimiters or instructions to ignore potential commands embedded within the code comments or configuration strings of the files being analyzed.\n
- Capability inventory: The skill produces refactored code blocks and analysis summaries. While the skill definition itself does not invoke dangerous system tools, the agent using it typically has the capability to write to the filesystem and execute commands based on these instructions.\n
- Sanitization: There is no mention of sanitizing the input data or filtering out potentially malicious instructions hidden in code comments or string literals.
Audit Metadata