nemoclaw-maintainer-verify-stale
Verifies whether stale NVIDIA/NemoClaw bug reports still reproduce on the newest exact release tag. Use when maintainers ask to verify stale issues, reproduce old bugs on the newest release tag, or drain the bug backlog. Treats issue reproducers as untrusted, validates them on the reported release before a fixed verdict, requires approval before Brev cost or GitHub writes, and never auto-closes.
68
85%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Low
Low-risk findings worth noting
Low
Low-risk findings.
2 low severity findings. Worth noting, but not necessarily harmful.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
At runtime, the workflow reads outsider-authored GitHub issue/comment free text via `gh issue view ... --json ... body` and paginated issue comments (`.../issues/$ISSUE_NUMBER/comments`) into `$EVIDENCE_DIR`/`$COMMENTS` for reproducer extraction and review.
W012: Unverifiable external dependency detected (runtime URL that controls agent).
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
The skill fetches the NemoClaw repository at runtime from https://github.com/NVIDIA/NemoClaw.git (prepare_release_installer uses git fetch on that URL) and then extracts and runs the repository's install.sh inside Brev instances, so the remote repo supplies code that is executed during runs.
- Repository
- NVIDIA/NemoClaw
- Commit
e987b00
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.