gh-project-scope
Pass
Audited by Gen Agent Trust Hub on Mar 3, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill makes extensive use of the
gh(GitHub CLI) tool via Bash to manage repository resources. It performs actions likegh apicalls, creating labels, and creating or editing issues. - [COMMAND_EXECUTION]: In Step 7, the skill retrieves an existing issue's body using
gh issue viewand interpolates that output directly into a shell command line to edit the issue. If an issue body contains malicious shell sequences (e.g., backticks or subshell expansions), it could lead to command injection when the agent executes the edit command. This constitutes a vulnerability to indirect input poisoning. - Ingestion points: Step 7 reads existing issue bodies from GitHub via
gh issue view. - Boundary markers: None; the output is interpolated directly into a double-quoted string in a shell command.
- Capability inventory: Full access to the
Bashtool andghCLI. - Sanitization: None performed on the retrieved data before shell interpolation.
Audit Metadata