brightdata-cli
Audited by ZeroLeaks on Apr 15, 2026
The skill's SKILL.md is mostly readable, but carries a transparency concern around remote script execution without a clear review boundary, which weakens pre-use reviewability and contributes to the AT_RISK verdict. Instruction/data separation stays reasonable—nothing in the skill strongly pushes the agent to treat external content as trusted policy. However, behavior analysis was not run, so it's not possible to confirm whether loading this skill materially changes downstream behavior compared to a no-skill baseline. The scan passed on prompt-injection signals, but the combination of limited behavioral validation and the unresolved remote-execution concern means confidence is medium—finite testing here does not rule out risk in all scenarios.
The skill has 1 transparency concern that weaken pre-use reviewability, mainly around remote script execution without review boundary.
The scanned skill keeps data and instructions reasonably separate and does not strongly encourage the agent to treat external content as policy.
Behavior analysis was not run.
Remote script execution without review boundary