Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
Jira REST API v3 Commons
v1.1.0Perform Jira Cloud daily tasks via REST API v3: search, create, update, assign issues; manage comments, worklogs; and handle boards, sprints, transitions.
⭐ 0· 444·1 current·1 all-time
byTCC@thecybercore
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
medium confidencePurpose & Capability
The skill's name/description (Jira Cloud REST v3 operations) aligns with the SKILL.md content: it instructs the agent to call Jira Platform v3 and Agile REST endpoints for issues, comments, worklogs, boards and sprints. However, the runtime instructions mandate multiple ATREST_ environment variables (base URL, auth mode, email, API token or bearer token, etc.) which are necessary for the described functionality, yet the registry metadata lists no required env vars or primary credential. That registry/manifest omission is inconsistent and could lead to the platform not prompting for the credentials the skill actually needs.
Instruction Scope
SKILL.md explicitly requires building and executing real CLI HTTP calls (curl on Linux or curl.exe/Invoke-RestMethod on Windows), writing JSON payloads to temporary files, base64-encoding credentials for Basic auth, parsing JSON responses, and paginating. Those actions are within the stated purpose (performing Jira REST operations) but give the skill the ability to execute arbitrary outbound HTTP requests from the host and to read environment variables. The document forbids printing secrets, but the runtime behavior will depend on the agent/platform implementation (logging, stdout/stderr handling).
Install Mechanism
There is no install spec and no code files to execute — this is an instruction-only skill. That's lower risk from an install vector perspective because nothing new is written to disk by the skill package itself. The runtime contract does, however, instruct creating temp files for payloads during use.
Credentials
The SKILL.md requires sensitive environment values (ATREST_JIRA_BASE_URL, ATREST_JIRA_AUTH_MODE, ATREST_JIRA_EMAIL, ATREST_JIRA_API_TOKEN, or ATREST_JIRA_BEARER_TOKEN) which are appropriate for a Jira integration. The proportionality concern is that the registry metadata/manifest did not declare these requirements (it listed 'Required env vars: none' and 'Primary credential: none'), so a platform user may not be informed upfront that secrets are required. Also, because the skill runs CLI commands and base64-encodes credentials for basic auth, there is potential for accidental token exposure via logs or temp files if the host/agent doesn't protect them.
Persistence & Privilege
The skill does not request always:true and is user-invocable only. It does instruct creating temporary JSON files (e.g., /tmp/jira-body.json or $env:TEMP files) for request bodies, which is normal for reliable CLI requests. It does not ask to modify other skills or global agent configuration. Autonomous invocation is allowed by default (disable-model-invocation=false) — this is platform normal behavior but increases the impact if credentials are available to the agent.
What to consider before installing
This skill appears to correctly document how to call Jira Cloud REST endpoints and requires Jira credentials to operate. Before installing or enabling it, confirm the platform will: 1) prompt you to supply the required ATREST_* env vars (base URL and either API token+email for basic auth or a bearer token) and store them securely (not in plain repo files); 2) prevent CLI/log output from leaking secrets (check agent logging, stdout/stderr handling, and temp-file lifecycle); and 3) restrict the agent's outbound network access if you want to limit where it can send data. The main red flag is a packaging mismatch: the registry/manifest did not declare the required env vars even though SKILL.md mandates them — ask the publisher or your platform admin to reconcile that before use. If you need lower risk testing, run the commands manually in a controlled/test environment first (use a test Jira account/token and inspect temporary files and logs).Like a lobster shell, security has layers — review code before you run it.
latestvk97ffavvys9qrpqsqgxem7akfx836vtb
License
MIT-0
Free to use, modify, and redistribute. No attribution required.