spec-taskstoissues
Warn
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- COMMAND_EXECUTION (MEDIUM): The skill executes a local bash script located at
.specify/scripts/bash/check-prerequisites.sh. Since the content of this script is not provided, it represents a risk of arbitrary command execution with the user's privileges. - COMMAND_EXECUTION (LOW): The skill utilizes system commands including
git config --get remote.origin.urlto verify the repository andgh issue create/listto interact with GitHub. - PROMPT_INJECTION (LOW): The skill is susceptible to Indirect Prompt Injection (Category 8):
- Ingestion points: The skill reads and parses
tasks.md. - Boundary markers: No specific delimiters or 'ignore' instructions are used to separate task data from agent instructions.
- Capability inventory: The agent can execute the GitHub CLI and a local bash script.
- Sanitization: No evidence of sanitization or validation of the task descriptions before they are passed to the
ghcommand. - DATA_EXFILTRATION (SAFE): Reading the git configuration and task list is necessary for the skill's stated purpose of managing GitHub issues and does not appear to be malicious.
Audit Metadata