sandbox-fallback-execution-5eda7b
Fallback pattern for executing Python code when sandbox execution fails by writing scripts to disk and running via shell
64
76%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Critical
Do not install without reviewing
Fix and improve this skill with Tessl
tessl review fix ./benchmarks/gdpval/skills/sandbox-fallback-execution-5eda7b/SKILL.mdSecurity
2 findings: 1 critical severity, 1 medium severity. Installing this skill is not recommended: please review these findings carefully if you do intend to do so.
E006: Malicious code pattern detected in skill scripts.
What this means
Detected high-risk code patterns in the skill content — including its prompts, tool definitions, and resources — such as data exfiltration, backdoors, remote code execution, credential theft, system compromise, supply chain attacks, and obfuscation techniques.
Why it was flagged
This skill explicitly instructs bypassing sandbox isolation by writing arbitrary Python to disk and executing it (including installing packages), which enables remote code execution, potential data exfiltration, and persistence — a high-risk backdoor/enabling pattern.
W013: Attempt to modify system services in skill instructions.
What this means
The skill prompts the agent to compromise the security or integrity of the user’s machine by modifying system-level services or configurations, such as obtaining elevated privileges, altering startup scripts, or changing system-wide settings.
Why it was flagged
This skill explicitly directs the agent to write and execute arbitrary Python scripts on the host and to install packages via run_shell/pip, enabling modification of the machine state and execution of untrusted code even though it does not request sudo or system-level configuration changes.
- Repository
- HKUDS/OpenSpace
- Commit
c5a9c4b
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.