debug-info-remapping

Pass

Audited by Gen Agent Trust Hub on Apr 2, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to run a shell command (node scripts/index.mjs) using variables ($function_id, $pc_index) extracted from external stack traces provided by the user, creating a surface for potential command injection if parameters are not properly sanitized by the agent.- [COMMAND_EXECUTION]: The script scripts/index.mjs uses the import() function to dynamically load a JSON file from a path provided as a command-line argument.- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it processes untrusted error data to drive its workflow and script execution.
  • Ingestion points: User-supplied runtime error messages and stack traces as defined in the Workflow section of SKILL.md.
  • Boundary markers: None; the instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings when handling user error logs.
  • Capability inventory: Execution of local shell commands via the agent as described in the remapping workflow.
  • Sanitization: Not present in the prompt instructions; while the target script parses numbers, the agent is not directed to sanitize or escape the strings before passing them to the shell.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 2, 2026, 09:47 PM