cs-issue-fix
Pass
Audited by Gen Agent Trust Hub on Jul 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local Python script located at
.codestable/tools/codestable-worktree-gate.py. It uses a{slug}variable, which corresponds to an issue directory name, directly in shell command interpolation. This pattern creates a potential command injection vulnerability if the directory name contains shell-sensitive characters and is not sanitized by the executing agent. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection. Ingestion points: The agent reads data from issue reports, analysis documents, and the
.codestable/issues/directory. Boundary markers: There are no instructions to the agent to treat this data as untrusted or to ignore embedded instructions. Capability inventory: The agent has the ability to execute shell commands (python3,grep) and write files to the local system. Sanitization: No explicit validation or escaping of input data or file contents is performed before the data influences agent logic or command execution. - [COMMAND_EXECUTION]: The skill utilizes the
greputility to recursively search local directories based on user-provided keywords. Without proper input handling, this could lead to unintended search behavior or resource consumption.
Audit Metadata