cmd-speckit-taskstoissues
Pass
Audited by Gen Agent Trust Hub on Apr 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
git config --get remote.origin.urlto retrieve repository information. While used for the legitimate purpose of identifying the target repository, it represents an automated command execution surface.\n- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes data from external files (tasks.md) and interpolates this content into its task flow.\n - Ingestion points: File content from
tasks.mdand feature specification files are used to populate issue fields.\n - Boundary markers: No explicit delimiters are specified to isolate the file content from the agent's internal instructions.\n
- Capability inventory: The agent can execute shell commands (
git) and interact with external APIs (GitHub) to create issues and labels.\n - Sanitization: The skill instructs the agent to escape special characters in titles and bodies, which serves as a structural safety measure but does not mitigate instruction-based injection within the task descriptions.
Audit Metadata