ClawAudit verdict
panda-imagine
Multi-provider image generation skill that calls documented provider APIs (OpenAI, Google, DashScope, etc.) using user-configured API keys for its stated image generation purpose.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Permission integrity
network_out
Findings (8)
Pipe-to-shell pattern (curl | sh) — supply chain attack vector
SKILL.md · code · curl -fsSL https://jimeng.jianying.com/cli | bash
Pipe to bash — executes piped content as shell commands
SKILL.md · code · | bash
Possible hardcoded credential
references/config/first-time-setup.md · code · API_KEY="your-key
Dynamic import() — loads module at runtime
scripts/main.ts · prose · downgraded · import("
References child_process — can spawn system processes
scripts/providers/jimeng.ts · prose · downgraded · child_process
Uses spawn() — can execute external programs
scripts/providers/jimeng.ts · prose · downgraded · spawn(
Accesses sensitive environment variables
scripts/providers/azure.ts · prose · downgraded · process.env.AZURE_OPENAI_API_KEY
Base64 encoding/decoding
scripts/providers/google.ts · prose · downgraded · Base64Encode
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class A/D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
No declared permissions — minimal attack surface.
network_out Is this flag fair?
Thanks — recorded.