hai-rewrite-doc
Warn
Audited by Gen Agent Trust Hub on Jun 17, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to verify claims within untrusted documents against "runnable commands." This instruction potentially leads the agent to execute arbitrary shell commands provided by a malicious input document, posing a significant security risk.
- [PROMPT_INJECTION]: The skill has a high surface area for indirect prompt injection as it processes untrusted documentation to drive its verification and rewriting logic. 1. Ingestion points: User-provided rotted or drifted documents. 2. Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the workflow. 3. Capability inventory: The agent is authorized to read the codebase, check configuration files, and execute shell commands. 4. Sanitization: The skill does not provide any logic for sanitizing or validating commands or paths extracted from the processed document.
Audit Metadata