codebase-audit-pre-push
Pass
Audited by Gen Agent Trust Hub on Aug 8, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to Indirect Prompt Injection because the agent is instructed to read and process every file in a codebase line-by-line. Malicious instructions embedded in the code, comments, or data files of the project being audited could be executed or influence the agent's behavior.
- Ingestion points: All files within the targeted codebase (SKILL.md).
- Boundary markers: No boundary markers or instructions to disregard embedded commands are present.
- Capability inventory: File deletion, file modification, and execution of audit tools (npm audit).
- Sanitization: No sanitization or validation of the ingested code content is specified.
- [COMMAND_EXECUTION]: The skill instructs the agent to perform autonomous destructive operations, such as the immediate deletion of various file types (logs, build artifacts, temporary files, node_modules) without requiring user confirmation for most categories.
Audit Metadata