Safe Skill

AdvisoryAudited by Static analysis on Mar 16, 2026.

Overview

Detected: suspicious.dangerous_exec, suspicious.dynamic_code_execution, suspicious.env_credential_access (+2 more)

Findings (11)

critical

suspicious.dangerous_exec

Location: tests/real_clawhub/donghaozhang__qcut-toolkit/videocut/subtitles/scripts/subtitle_server.js:110
Finding: Shell command execution detected (child_process).

critical

suspicious.dangerous_exec

Location: tests/real_clawhub/donghaozhang__qcut-toolkit/videocut/talk-edit/scripts/review_server.js:74
Finding: Shell command execution detected (child_process).

critical

suspicious.dynamic_code_execution

Location: scan.py:153
Finding: Dynamic code execution detected.

critical

suspicious.dynamic_code_execution

Location: scripts/scan.py:153
Finding: Dynamic code execution detected.

critical

suspicious.dynamic_code_execution

Location: tests/adversarial/adv_05_comment_payload/hidden.py:9
Finding: Dynamic code execution detected.

critical

suspicious.dynamic_code_execution

Location: tests/malicious/mal_03_eval_dynamic/helper.py:9
Finding: Dynamic code execution detected.

critical

suspicious.env_credential_access

Location: tests/real_clawhub/assistant-design__clawflight/clawflight.js:31
Finding: Environment variable access combined with network send.

warn

suspicious.potential_exfiltration

Location: tests/real_clawhub/assistant-design__clawflight/clawflight.js:14
Finding: File read combined with network send (possible exfiltration).

warn

suspicious.potential_exfiltration

Location: tests/real_clawhub/donghaozhang__qcut-toolkit/videocut/subtitles/scripts/subtitle_server.js:21
Finding: File read combined with network send (possible exfiltration).

warn

suspicious.potential_exfiltration

Location: tests/real_clawhub/donghaozhang__qcut-toolkit/videocut/talk-edit/scripts/generate_review.js:28
Finding: File read combined with network send (possible exfiltration).

warn

suspicious.prompt_injection_instructions

Location: tests/malicious/mal_07_agent_hijack/SKILL.md:24
Finding: Prompt-injection style instruction pattern detected.