product-vision-audit
Pass
Audited by Gen Agent Trust Hub on Jul 17, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection. It processes untrusted data from external sources (Linear issue descriptions) and local codebase files (README, documentation) to generate reports and automated recommendations.
- Ingestion points: Data enters the context via
mcp__linear-server__get_issueand local file reads of the codebase. - Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands within the ingested data.
- Capability inventory: The skill has permissions to execute shell commands (grep, ls, glob), write files to the disk, and create new issues in Linear.
- Sanitization: There is no evidence of filtering or sanitization of the external content before processing.
- [COMMAND_EXECUTION]: The skill employs dynamic code execution for data management. Specifically, it instructs the agent to use Python scripts to slice large data payloads if tool output limits are exceeded.
- [COMMAND_EXECUTION]: The skill performs active filesystem operations including directory creation (
mkdir -p) and content searching (grep,glob) to gather audit evidence.
Audit Metadata