Security audit

Jira Flow Skill Free

Security checks across malware telemetry and agentic risk

Overview

This Jira skill is not malicious, but it asks for command execution and Jira credentials to make live changes to project data without enough scoping or confirmation guidance.

Review before installing if this would connect to a real company Jira. Use a least-privilege Atlassian token, restrict JIRA_BOARD where possible, avoid putting tokens in shared shell profiles or logs, and require explicit confirmation for status changes, assignments, comments, issue creation, and worklog entries.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
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
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (4)

Vague Triggers

Medium

Confidence: 89% confidence
Finding: The activation description is broad enough to match many ordinary project-management prompts, increasing the chance the skill will be invoked in contexts where the user did not clearly intend Jira-side actions. Because the skill exposes `exec` and supports write operations like assignment, status changes, comments, and task creation, overbroad triggering can lead to unintended remote modifications.

Vague Triggers

Medium

Confidence: 92% confidence
Finding: The keyword coverage list includes very broad phrases such as project management, planning, progress tracking, and collaboration, which are common across many benign requests unrelated to Jira. In a skill with command execution and write-capable API workflows, such unconstrained triggers materially raise the risk of accidental activation and unintended actions against remote Jira data.

Missing User Warnings

Medium

Confidence: 94% confidence
Finding: The documentation presents mutating actions—state changes, assignments, comments, task creation, and worklog logging—without clearly warning that they modify live Jira Cloud records. In the context of an agent skill using `exec`, users may reasonably assume a dry-run or informational mode, so the absence of a prominent modification warning increases the chance of unintended changes to production project data.

Missing User Warnings

Medium

Confidence: 88% confidence
Finding: The skill instructs users to set Jira credentials in environment variables but does not include a clear privacy and handling warning about how those secrets are used, transmitted to Jira Cloud, and potentially exposed through shell history, logs, subprocesses, or misconfigured environments. In a skill that relies on command execution, insufficient secret-handling guidance increases the chance of credential leakage or unsafe operational practices.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.