Use only when the user explicitly invokes /roborev-setup-review
70%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Critical
Do not install without reviewing
Fix and improve this skill with Tessl
tessl review fix ./internal/skills/claude/roborev-setup-review/SKILL.mdDetected a prompt injection in the skill instructions. The skill contains hidden or deceptive instructions that fall outside its stated purpose and attempt to override the agent’s safety guidelines or intended behavior.
The skill is a disclosed, approval-gated setup helper for roborev, but its instruction to retry commands with `dangerouslyDisableSandbox: true` on permission errors weakens a sandbox protection beyond what a status check needs, so it is sketchy rather than malicious.
The skill prompts the agent to compromise the security or integrity of the user’s machine by modifying system-level services or configurations, such as obtaining elevated privileges, altering startup scripts, or changing system-wide settings.
Gate 1 passes: the skill offers an available operation, `roborev init --from-skill`, that installs Git hooks, starts a persistent background service, and edits `.gitignore`, and it also allows global config writes, but no explicit irreversible operational loss is established, so the tier is low.
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.
The required workflow configures and runs CI reviews of pull requests (`[ci] panel`, `roborev init gh-action`), and those reviewers read PR diffs and metadata that outsiders can submit to a public repository, without the agent selecting a specific item first.
kenn-io/roborev
7e74ef7
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.