Skillv1.0.0

ClawScan security

jira-expert · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

BenignMar 11, 2026, 3:43 PM

Verdict: benign
Confidence: medium
Model: gpt-5-mini
Summary: The skill's files and runtime instructions match a Jira-focused purpose and do not request unrelated credentials or installs, but it assumes an external 'mcp' Jira integration and does not declare how Jira credentials are provided — you should confirm where API credentials come from before using it.
Guidance: This skill appears to be what it says — Jira guidance plus two helper scripts for building JQL and validating workflows. Before installing: (1) confirm where Jira credentials/API token are provided (the skill doesn't declare required env vars); (2) verify the 'mcp' CLI or equivalent integration is available and trusted on your agent runtime; (3) review the included Python scripts if you plan to execute them locally (they appear to be offline utilities, but inspect for network calls if you have concerns); (4) because the skill's source/homepage is unknown, prefer running it in a sandbox or test project first and avoid giving it access to sensitive production Jira projects until you confirm auth and behavior.

Purpose & Capability: okName/description, SKILL.md content, reference docs, and the two included Python helpers (JQL builder and workflow validator) are all coherent with a Jira configuration / automation / JQL assistance skill.
Instruction Scope: noteSKILL.md instructs the agent to run 'mcp jira ...' CLI commands and provides detailed, Jira-specific guidance. It does not instruct the agent to read unrelated system files or exfiltrate data. However, it implicitly requires an external 'mcp' integration and Jira credentials which are not described — confirm how the agent will authenticate before executing live operations.
Install Mechanism: okNo install spec or remote download; the skill is instruction-heavy with local helper scripts included. Nothing in the manifest indicates the installer will fetch or execute code from arbitrary URLs.
Credentials: noteThe skill declares no required environment variables or credentials even though performing Jira operations normally requires API credentials or a configured CLI. This omission could be benign if the hosting platform provides credentials, but you should verify where and how Jira auth is supplied. No other unrelated secrets or config paths are requested.
Persistence & Privilege: okalways:false and model invocation is allowed (the platform default). The skill does not request elevated platform-wide persistence or attempt to modify other skills; nothing here indicates excessive privilege.