openclaw-docs-audit
Fail
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: CRITICALREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill documentation in
SKILL.mdincludes a command that downloads a script from a remote URL and pipes it directly to the bash shell (curl -fsSL https://openclaw.ai/install.sh | bash). This pattern allows for the execution of arbitrary remote code from an untrusted third-party domain without integrity verification. - [PROMPT_INJECTION]: The skill is designed to audit external content, making it susceptible to indirect prompt injection where instructions hidden in the data could override agent behavior.
- Ingestion points: The skill fetches release note bodies from GitHub using
gh release viewand scrapes external documentation fromdocs.openclaw.aiusing WebFetch. - Boundary markers: There are no markers or instructions defined to delimit the external content or warn the agent to ignore embedded commands within the fetched data.
- Capability inventory: The skill has the ability to execute shell commands via
scripts/audit.shand perform network operations. - Sanitization: No sanitization, escaping, or validation steps are performed on the external text before it is processed by the agent.
Recommendations
- HIGH: Downloads and executes remote code from: https://openclaw.ai/install.sh - DO NOT USE without thorough review
- AI detected serious security threats
Audit Metadata