nemoclaw-maintainer-release-notes
Pass
Audited by Gen Agent Trust Hub on Aug 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes standard command-line tools including
git,gh(GitHub CLI), andnpm. These tools are used to retrieve release data, verify tags, and process pull request metadata from the NemoClaw repository. - [PROMPT_INJECTION]: The skill processes data from GitHub pull requests, which represents an indirect prompt injection surface where untrusted external content could influence the agent's drafting behavior.
- Ingestion points: GitHub pull request metadata retrieved via
gh pr viewandgh api compareas described inSKILL.md. - Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands within the ingested PR data.
- Capability inventory: The skill has the capability to execute shell commands (
git,gh,npm) and write Markdown files to the local file system. - Sanitization: There is no explicit sanitization or filtering of the retrieved pull request content before it is incorporated into the draft.
Audit Metadata