domain-modeling
Pass
Audited by Gen Agent Trust Hub on Aug 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill directs the agent to execute shell commands, specifically
git rev-parse --git-common-dir, to identify the project root and documentation locations. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it interprets content from untrusted external files (glossaries, ADRs, and source code) to guide its logic. \n
- Ingestion points: Reads project files including
CONTEXT.md,CONTEXT-MAP.md, and various source code files to build the domain model. \n - Boundary markers: Absent. The skill does not instruct the agent to use delimiters or treat the ingested content as potentially malicious instructions. \n
- Capability inventory: The skill grants the agent file read/write permissions for documentation updates and shell command execution capabilities. \n
- Sanitization: Absent. There is no filtering or validation of the text read from project files before it is processed by the agent.
Audit Metadata