openspec-verify-change
Pass
Audited by Gen Agent Trust Hub on Feb 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes the
openspecCLI, a tool associated with the vendor mtymek. It constructs shell commands by interpolating variables, such asopenspec status --change "<name>" --json. This pattern is susceptible to command injection if the<name>parameter contains malicious shell metacharacters. - [PROMPT_INJECTION]: The skill reads and evaluates content from external project files, which creates an attack surface for indirect prompt injection.
- Ingestion points: The agent reads and processes data from
tasks.md,design.md, and specification files withinopenspec/changes/. - Boundary markers: The instructions do not define boundary markers or include directives to ignore instructions that might be embedded in the analyzed files.
- Capability inventory: The skill has permissions to read local files and execute the
openspecCLI tool. - Sanitization: There is no explicit sanitization or validation of the data ingested from the file system before it is analyzed by the agent.
Audit Metadata