land-stack
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill performs command-line operations using the GitHub CLI and executes a local script.
- It uses
gh stack mergeandgh pr mergeto perform squash merges on pull requests. - It executes a local script located at
scripts/pullto synchronize the trunk branch after merging is complete. - [INDIRECT_PROMPT_INJECTION]: The skill ingests external data from GitHub pull requests, creating a surface for indirect instructions to influence agent behavior.
- Ingestion points: Pull request metadata including titles, numbers, and branch names retrieved via
gh pr viewandgh stack viewas described inSKILL.md. - Boundary markers: No explicit delimiters or instructions to ignore embedded content are used when the agent processes the PR metadata.
- Capability inventory: The skill possesses capabilities to merge code into the base branch, view sensitive PR data, and execute scripts in the local environment.
- Sanitization: The skill does not implement sanitization or validation of the ingested pull request metadata before it is used to determine merging logic.
Audit Metadata