create-dashboard-playbook
Pass
Audited by Gen Agent Trust Hub on Mar 5, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill generates a new executable skill file in the .claude/skills/ directory that includes functional Bash commands for data extraction and processing.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it incorporates content from untrusted workspace files into the generation of a new skill.
- Ingestion points: The skill reads CLAUDE.md, README.md, and various data files (*.json, *.yaml) or logs to determine dashboard metrics.
- Boundary markers: No explicit delimiters or 'ignore' instructions are used when processing external data sources during the generation phase.
- Capability inventory: The generated 'update-dashboard' skill is granted permissions to use Read, Write, Bash, and Glob tools.
- Sanitization: There is no evidence of content sanitization or validation of the data ingested from the workspace before it is used to define the logic of the generated skill.
Audit Metadata