skills/openclaw/skills/ClawdStrike/Gen Agent Trust Hub

ClawdStrike

Pass

Audited by Gen Agent Trust Hub on Mar 2, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is a defensive audit tool that gathers system information and configuration details to generate a security report. All operations are local and findings are summarized with redaction of sensitive data.
  • [COMMAND_EXECUTION]: The skill executes a predefined set of local system utilities (e.g., uname, id, ss, ufw, find) through scripts/collect_verified.sh to gather evidence for its audit. These commands are governed by a strict internal allowlist.
  • [PROMPT_INJECTION]: The SKILL.md file contains explicit safety rules that instruct the agent to treat third-party skill files as untrusted data and to ignore any instructions found within them, which serves as a mitigation against indirect prompt injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 2, 2026, 01:55 AM