d2c-audit
Pass
Audited by Gen Agent Trust Hub on Apr 13, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it ingests untrusted data from the user's codebase for analysis.\n
- Ingestion points: Analyzes all project source files (e.g., .tsx, .vue, .css) and configuration files located in .claude/d2c/ as specified in SKILL.md.\n
- Boundary markers: There are no explicit boundary markers or instructions to the agent to disregard natural language commands embedded in the source code or JSON files being read.\n
- Capability inventory: Employs Read, Bash, Glob, and Grep tools, with the ability to write to the filesystem when the --fix argument is provided in SKILL.md.\n
- Sanitization: The skill does not perform sanitization or validation of the ingested file content before it enters the agent's prompt context.
Audit Metadata