stack
Pass
Audited by Gen Agent Trust Hub on Mar 21, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions for executing a local CLI tool located at
/Users/jean-patricksmith/digital/leviathan/plugins/prompt-stack/src/cli.tsusing thebunruntime. - [COMMAND_EXECUTION]: It references hardcoded absolute file paths within a specific user's directory structure.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its handling of external report and stack data.
- Ingestion points: The contents of report files passed to the
--reportparameter and prompt bodies accessed via thenextcommand. - Boundary markers: Absent; there are no delimiters or protective instructions provided when processing this data.
- Capability inventory: Includes executing local scripts and writing to the file system.
- Sanitization: Absent; the skill does not describe any sanitization steps for the data it processes.
Audit Metadata