Security audit

缺陷猎人

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly a coherent bug-analysis helper, but its documented Jira and ZenTao integrations can send sensitive bug data and API tokens to external systems without clear consent or destination validation.

Review this skill before installing. Use it for local bug analysis by default, and only enable Jira or ZenTao integration with trusted HTTPS URLs, least-privilege tokens, and explicit confirmation before creating tickets or sending logs, screenshots, stack traces, customer data, or security findings.

A.I.G

Vulnerability Patterns

Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
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

Findings (2)

T09 · Insecure Skill Coding Practices

Error

Location: SKILL.md:257
Finding: Jira API token disclosure through an unvalidated service URL
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Error

Location: SKILL.md:293
Finding: ZenTao API token disclosure through an unvalidated service URL
Content: View full analysis
` to that destination. 5. The destination records the API token. 6. The attacker reuses the credential against the legitimate ZenTao service within the token's assigned permissions. ### Impact Assessment The attacker can obtain the ZenTao API token and exercise any permissions granted to it. Depending on token scope, this may expose private bug records, product metadata, int ...[truncated 219 chars]
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (5)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The description says to use this skill whenever the user needs to analyze bug causes, classify defects, generate bug reports, track fixes, or mentions a wide list of terms such as "问题定位" and "根因分析". These triggers are expansive and lack explicit boundaries or negative examples, making it unclear when this skill should activate versus a more general troubleshooting or analysis skill.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill’s natural-language description and operating instructions are entirely in Chinese and do not indicate that users may choose another language. This can violate language or locale policy when a skill effectively constrains interaction to a specific language without opt-in or documented justification.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The documentation includes Jira and ZenTao integrations but does not clearly warn that bug descriptions, logs, screenshots, or other defect data may be transmitted to external systems. Because bug artifacts often contain sensitive internal details, stack traces, PII, or security-relevant information, lack of disclosure and consent increases the chance of unintended data leakage.
Content: No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The skill is presented as a bug analysis/tracking assistant, but it also documents code to create Jira issues, which expands its scope from analysis into state-changing actions against an external system. That creates a real risk of unintended ticket creation, spam, disclosure of sensitive bug details to third-party services, or misuse if the skill is invoked in contexts where the user only expected analysis.
Content: No source excerpt is available for this finding.

External Transmission

Medium

Category: Data Exfiltration
Confidence: 96% confidence
Finding: The documented requests.post call sends structured issue data to Jira, which is an external transmission sink. In this skill's context, that means potentially sensitive bug details can leave the current environment and be persisted in an external platform, and the action is also state-changing rather than purely analytical.
Content: Scanner excerpt · SKILL.md (reported line 286)May include surrounding context.
"labels": labels or [] } } response = requests.post(url, headers=self.headers, json=data) return response.json()

text

Static analysis

No suspicious patterns detected.