Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
Fortisase Audit
v1.0.0Fortinet FortiSASE audit — Secure Web Gateway policy review, ZTNA application gateway assessment, thin edge FortiGate integration validation, SD-WAN security...
⭐ 0· 31·1 current·1 all-time
byVahagn Madatyan@vahagn-madatyan
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
medium confidencePurpose & Capability
The SKILL.md content describes a FortiSASE audit and the API endpoints it calls; that purpose legitimately requires FortiCloud/FortiSASE API access and occasionally thin-edge FortiGate credentials. However the registry metadata provided to the platform lists no required environment variables while the SKILL.md metadata and procedure reference a FORTISASE_API_TOKEN and explicit username/password/client_id flows. This mismatch between declared registry requirements and the runtime instructions is an incoherence to verify.
Instruction Scope
The instructions call FortiCloud/FortiSASE REST APIs and (optionally) directly authenticate to thin-edge FortiGates. They include explicit examples requiring FortiCloud username/password/client_id and thin-edge admin_user/admin_password. Those are sensitive and the SKILL.md does not specify how secrets are provided/stored or whether persistent storage is used. The instructions otherwise stay within the stated audit scope and point only to Fortinet domains for egress.
Install Mechanism
This is instruction-only (no install spec, no code files). That minimizes disk/write risk — there is no installer or downloaded executable to review.
Credentials
SKILL.md metadata requires FORTISASE_API_TOKEN and the procedure references FortiCloud username/password and client_id plus optional thin-edge admin credentials. The registry listing showed no required env vars and no primary credential — an inconsistency. Requesting API tokens and device admin credentials is proportionate to the audit task if they are strictly read-only, but the skill does not document least-privilege guidance or where credentials must be supplied (env vs interactive), which increases risk.
Persistence & Privilege
The skill is not 'always:true' and is user-invocable; it can run autonomously by default (platform normal). Because it needs sensitive credentials, the user should consider not storing long-lived credentials globally. The skill itself does not appear to require modification of other skills or system settings.
Scan Findings in Context
[no-findings] expected: Regex scanner had nothing to analyze because this is an instruction-only skill with no code files. That absence is expected but means the runtime instructions are the primary security surface.
What to consider before installing
This skill appears to do what it says (FortiSASE audit) but before installing: 1) Verify the skill source/publisher (homepage and author are missing). 2) Confirm exactly which credentials it needs and supply least-privileged, read-only API tokens rather than full admin passwords where possible. 3) Do not store long-lived admin passwords or tokens as global environment variables — prefer ephemeral credentials or interactive input. 4) If you must provide thin-edge admin credentials, test in a non-production environment first. 5) If you do not trust the publisher, decline to install; alternatively, ask the publisher to update the registry metadata to list required env vars (e.g., FORTISASE_API_TOKEN) and clarify credential handling and token storage. 6) Consider disabling autonomous execution or ensuring the agent cannot auto-run the skill with stored credentials until you have validated behavior.Like a lobster shell, security has layers — review code before you run it.
latestvk97b53m0dr490q52bck6dqwcwx840xaa
License
MIT-0
Free to use, modify, and redistribute. No attribution required.