cs-issue-report
Pass
Audited by Gen Agent Trust Hub on Jun 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [SAFE]: Extensive analysis of the skill's instructions reveals no malicious intent. The defined actions are confined to document generation and project-specific issue tracking.
- [COMMAND_EXECUTION]: The skill commands the agent to use tools for directory listing and code searching (Grep/Read). These operations are used exclusively to support the issue triaging process and do not exceed the scope of a developer assistant.
- [PROMPT_INJECTION]: The skill processes user-supplied data and codebase content, creating a surface for indirect prompt injection. 1. Ingestion points: User responses to interview questions and source code retrieved during discovery. 2. Boundary markers: The skill relies on markdown template structures to separate data. 3. Capability inventory: The agent has permissions to read from and write to the local file system. 4. Sanitization: No explicit sanitization or validation of the ingested external content is mentioned.
Audit Metadata