define-domain-language
Pass
Audited by Gen Agent Trust Hub on Jul 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute a shell command (
grep -rh "^class \\|^module " lib/ app/ --include="*.rb" | sort) to identify existing Ruby class and module definitions. This is a legitimate operation within the context of a Ruby/Rails development skill used for terminology discovery. - [PROMPT_INJECTION]: The skill contains a surface for indirect prompt injection by design.
- Ingestion points: It processes data from potentially untrusted external sources, including PRDs, tickets, and project documentation as described in
SKILL.md. - Boundary markers: No explicit delimiters or instructions are provided to the agent to distinguish between the skill's instructions and commands that might be embedded in the ingested documents.
- Capability inventory: The skill has the capability to execute shell commands (
grep) and access the local filesystem (SKILL.md). - Sanitization: There is no evidence of sanitization or validation of the input data before it is processed by the agent.
Audit Metadata