Env credential access
Critical
- Finding
- Environment variable access combined with network send.
Art Process Video
Security checks across static analysis, malware telemetry, and agentic risk
Overview
This appears to be a purpose-aligned WeryAI video-generation skill, but it requires an API key and confirmed runs can spend WeryAI credits.
Install only if you trust the source, keep WERYAI_API_KEY secret and rotatable, verify WERYAI_BASE_URL/WERYAI_MODELS_BASE_URL are unset or trusted, and confirm parameters before any `wait` run because it can consume paid credits.
Static analysis
VirusTotal
VirusTotal findings are pending for this skill version.
Risk analysis
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
#
ASI03: Identity and Privilege Abuse
Medium
What this means
Anyone with this key could potentially use the associated WeryAI account or credits within that provider's permissions.
Why it was flagged
The script authenticates outbound API requests with the user-provided WeryAI API key. This is expected for the stated service, but it is still a sensitive account credential.
Skill content
Authorization: `Bearer ${apiKey}` ... fetch(fullUrl, { method, headers, body: body != null ? JSON.stringify(body) : undefined })Recommendation
Use a rotatable or limited WeryAI key if available, keep it out of the skill package, and verify URL override environment variables are unset or trusted before running.
#
ASI02: Tool Misuse and Exploitation
Medium
What this means
Repeated or mistaken runs could spend WeryAI credits.
Why it was flagged
The documented workflow can submit paid generation jobs. This is purpose-aligned and disclosed, but users should notice the credit/charge impact before confirming.
Skill content
Each successful `wait` run consumes WeryAI credits; re-running creates new paid tasks.
Recommendation
Review the full prompt and parameters in the confirmation table before approving a run, and avoid unnecessary retries.
#
ASI04: Agentic Supply Chain Vulnerabilities
Info
What this means
Users have less external context for deciding whether to trust the skill with an API key.
Why it was flagged
The registry does not provide an external source or homepage for provenance. No remote installer or dependency chain is shown, but provenance is limited.
Skill content
Source: unknown; Homepage: none
Recommendation
Review the included script and install/run it only if you trust the package source.