typescript-expert
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION] (LOW): The
scripts/ts_diagnostic.pyscript executes system commands via a shell.\n - Evidence:
subprocess.run(cmd, shell=True)is used in therun_cmdhelper function to executenpx,node, andgrep.\n - Risk: While the command strings are currently static, the use of
shell=Trueis a security anti-pattern.\n- [PROMPT_INJECTION] (LOW): The skill is susceptible to indirect prompt injection from the codebase it analyzes.\n - Ingestion points: The script reads and processes
package.json,tsconfig.json, and all TypeScript files in thesrc/directory.\n - Boundary markers: No boundary markers or 'ignore' instructions are used when outputting file contents or analysis results to the agent.\n
- Capability inventory: The script performs file reads and executes subprocesses based on project structure.\n
- Sanitization: No sanitization is performed on the data read from the local filesystem before it is displayed.
Audit Metadata