gstack-openclaw-skills
Pass
Audited by Gen Agent Trust Hub on Mar 22, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill suite performs automated local command execution as part of its core functionality. Specialized components like
ship/SKILL.mdandqa/SKILL.mdexecute git commands (e.g.,git merge,git push) and test runners (e.g.,pytest,npm test) to automate the software development lifecycle. These actions are consistent with the skill's stated purpose. - [INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it is designed to ingest and process untrusted data from the local repository, such as source code and git diffs, in the
review/SKILL.mdandqa/SKILL.mdtools. - Ingestion points: Source code files and git diffs (e.g.,
git diff origin/main...HEAD) are read into the agent's context for analysis. - Boundary markers: The instructions do not define explicit boundary markers to separate the ingested code from the agent's system instructions.
- Capability inventory: The skill has the capability to execute shell commands, write files to the local system via
state_manager.py, and create Pull Requests on remote repositories. - Sanitization: There is no evidence of sanitization or filtering of the ingested source code content before it is processed by the LLM.
Audit Metadata