Security audit

Roast Chef 💀

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed roast generator with local scripts and reference text, with no evidence of hidden access, persistence, exfiltration, or destructive behavior.

Install only if you want an opt-in comedic roast style. Be aware that broad phrases like 'critique' or 'rate my' may produce harsher feedback than a normal review, and non-Chinese users may need to explicitly request English output.

A.I.G

Vulnerability Patterns

Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (6)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The trigger list is overly broad for a generally available skill: phrases like 'rate my', 'critique', and 'call me out' are common in many benign conversations and can cause the roast persona to activate when the user did not explicitly request this mode. In context, unintended invocation is more dangerous because the skill is designed to produce harsh, insulting output, increasing the risk of surprise harassment, unsafe tone shifts, or policy-violating responses in otherwise normal chats.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The body of the skill instructions is written entirely in Chinese, which effectively constrains the skill's operating language for core behavior and examples. Although line 31 mentions a '--language zh/en' option, the surrounding instructions do not clearly state that language choice is user-selectable by default or that the skill should adapt to the user's preferred language.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: This markdown file presents all user-facing content in Chinese and does not indicate that the skill is Chinese-only, region-specific, or user-selectable by locale. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The roast function sets language to "zh" by default, which forces a specific locale unless the caller explicitly overrides it. Under the policy, a language constraint should be user-selected or clearly justified; here the code supports both zh and en but still defaults to Chinese automatically.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The command-line interface defines --language choices of zh and en but defaults to zh, so users who do not specify a language are forced into a specific language. This is a natural-language policy issue because the skill does not offer a neutral prompt or explicit opt-in before selecting the locale.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 89% confidence
Finding: This code embeds the skill’s personas and output text primarily in Chinese, which effectively forces a specific language/locale for users. The policy allows locale constraints only when they are explicitly justified or when the user is given a language choice, neither of which appears here.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.