tls-certificate-analysis
Fail
Audited by Gen Agent Trust Hub on Mar 9, 2026
Risk Level: HIGHCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill performs shell-based operations in
extract_certificate_metadata,extract_sans, andcheck_protocol_supportusing the{domain}variable. The variable is interpolated directly intobashcommands likeopenssl s_client -connect {domain}:443. This pattern is highly susceptible to command injection if the input contains shell metacharacters. - [PROMPT_INJECTION]: By accepting unsanitized input for use in shell commands, the skill allows an attacker to bypass intended logic and execute arbitrary system commands via a specially crafted domain string.
- [COMMAND_EXECUTION]: The skill configuration defines execution hooks (
pre_network_skill_hook.shandpost_skill_logging_hook.sh) using relative paths that reach outside the skill's directory structure. This configuration triggers the execution of shell scripts during the tool's lifecycle.
Recommendations
- AI detected serious security threats
Audit Metadata