style-audit
Pass
Audited by Gen Agent Trust Hub on Aug 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands to manage its auditing scope and verification. It uses
git diff --name-onlyto identify changed files andbash scripts/check-style.shto run mechanical style checks. These are standard operations for a development-focused authoring tool. - [PROMPT_INJECTION]: The skill operates by ingesting and processing content from various repository files, which creates an attack surface for indirect prompt injection.
- Ingestion points: The skill reads content from the
skills/andrules/directories, as well as project README files. - Boundary markers: There are no explicit instructions for the agent to ignore or delimit instructions found within the audited text.
- Capability inventory: The agent has the ability to read local files, execute shell commands, and modify the
scripts/check-style.shfile by appending new banned terms. - Sanitization: The instructions do not specify any sanitization or validation of the text content before it is processed by the agent.
Audit Metadata