grace-status
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes
grace statusandgrace lintcommands to analyze project states. These operations are limited to reporting and linting based on the provided project path. - [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes output from the
graceCLI tool, which represents a potential surface for indirect prompt injection if the analyzed project files contain malicious content that is reflected in the tool's output. - Ingestion points: The agent reads JSON and text output from
grace status --jsonandgrace lint(found inSKILL.md). - Boundary markers: No specific boundary markers or instructions to ignore embedded content are defined in the task description.
- Capability inventory: The skill is restricted to executing the
graceCLI tool for status reporting and integrity checks. - Sanitization: There is no evidence of explicit sanitization or filtering applied to the CLI output before it is processed by the agent.
Audit Metadata