openspec-new-change
Pass
Audited by Gen Agent Trust Hub on Jul 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill executes subcommands of the
openspecCLI, such asnew change,status, andinstructions, to scaffold projects and retrieve metadata based on user input. - [PROMPT_INJECTION]: The skill ingests untrusted user input via the
AskUserQuestiontool, creating a surface for indirect prompt injection attacks. - Ingestion points: User descriptions captured in
SKILL.md. - Boundary markers: Absent; the skill lacks explicit delimiters for separating user input from instructions.
- Capability inventory: Shell command execution capabilities for the
openspecCLI. - Sanitization: The skill provides a guardrail instructing the agent to derive a kebab-case name and validate it, prompting the user for correction if the format is invalid.
- [EXTERNAL_DOWNLOADS]: The skill documentation specifies that the
openspecCLI is a prerequisite. No logic is included to automatically download or install external code or dependencies.
Audit Metadata