aider
Pass
Audited by Gen Agent Trust Hub on May 14, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides a series of bash command templates for running the
aiderCLI tool. These commands are intended for legitimate AI pair programming tasks. - [PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection by accepting user-provided messages and passing them as arguments to the
aidercommand. - Ingestion points: Input is ingested via the
--messageparameter in the shell command templates inSKILL.md. - Boundary markers: The skill uses double quotes to wrap the message content (e.g.,
--message "YOUR PROMPT HERE"). - Capability inventory: The
aidertool is capable of performing file system writes, reading project files, and creating git commits. - Sanitization: The skill relies on standard shell quoting; no additional sanitization or instruction-filtering is documented.
Audit Metadata