typescript-debugging
Pass
Audited by Gen Agent Trust Hub on Jul 31, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill involves the agent reading and analyzing local source code and configuration files. This introduces a surface for indirect prompt injection, where malicious instructions hidden in code comments or data files could attempt to override agent behavior during the debugging process.
- Ingestion points: User project files accessed via Read, Grep, and Glob tools.
- Boundary markers: Absent; the skill does not define specific delimiters for untrusted file content.
- Capability inventory: Access to Bash, Write, and Edit tools.
- Sanitization: None specified for content extracted from files.
- [COMMAND_EXECUTION]: The skill instructs the agent to use the Bash tool to execute various Bun CLI commands for debugging, testing, and profiling. While these are intended functions, they represent the execution of shell commands based on the context of the project being analyzed.
Audit Metadata