techartist-workflow
Pass
Audited by Gen Agent Trust Hub on Mar 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The workflow involves generating code, performing git commits for asset and code changes, and running validation scripts as part of the implementation cycle.
- [EXTERNAL_DOWNLOADS]: The skill utilizes standard tools such as WebSearch and Fetch MCP to retrieve implementation details and technical references from external sources.
- [PROMPT_INJECTION]: The skill ingests external data from CLI arguments ($arguments.message) and local configuration files (./.claude/session/pending-messages-techartist.json, prd.json), creating a surface for indirect prompt injection where task descriptions could contain malicious instructions.
- Ingestion points: Data is read from CLI arguments, PRD files, and session-specific JSON files in the .claude directory.
- Boundary markers: No explicit delimiters or isolation instructions are provided for the ingested content.
- Capability inventory: The skill possesses file writing capabilities, git execution permissions, and network access via search tools.
- Sanitization: No verification or filtering of incoming message content is implemented.
Audit Metadata