spec-driven-cancel
Pass
Audited by Gen Agent Trust Hub on Mar 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes
lsto verify the existence of the.spec-driven/directory and runs a Node.js script to list and delete changes. - [COMMAND_EXECUTION]: The skill utilizes scripts located via a relative path (
../../dist/scripts) pointing outside its immediate directory. - [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection (Category 8) by incorporating file and directory names directly into shell command arguments.
- Ingestion points: Change names are retrieved from the file system using
lsand script output as described inSKILL.md. - Boundary markers: The instructions do not define delimiters for the ingested data or provide instructions to ignore embedded commands within the names.
- Capability inventory: The skill is capable of executing shell commands and Node.js scripts through the agent.
- Sanitization: There is no evidence of sanitization or validation performed on the
<name>variable before it is passed to the shell for execution.
Audit Metadata