ClawAudit verdict
interop-forge
Fetches from network AND uses eval/Function
Integration architect skill that generates code for shared contracts and MCP servers; explicitly states it never reads or modifies env/credential files directly and all env var references are in generated code only, matching its legitimate stated purpose.
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.
What it does
These are capability combinations: each listed behavior occurs in the skill, but ClawAudit detects co-occurrence — it does not verify that one flows into another. Read the code to confirm a live chain.
Fetches from network AND uses eval/Function — the remote-code-execution pattern (data-flow not verified)
LLM05 · LLM06 · ASI05
Receives external input AND uses eval — the remote code-injection pattern (data-flow not verified)
LLM01 · LLM05 · ASI01 · ASI05
Encodes data AND uses eval — the obfuscated-execution pattern (atob + eval; data-flow not verified)
LLM05 · ASI05 · ASI10
Accesses credentials AND makes external network calls — potential credential theft
LLM02 · ASI03
Accesses credentials AND encodes data — may obfuscate stolen credentials
LLM02 · ASI03 · ASI04
Permission integrity
network_out
credential_access
Findings (3)
<script> tag in markdown — potential code injection
SKILL.md · prose · downgraded · <script>
Dynamic import() — loads module at runtime
SKILL.md · code · import("
Accesses sensitive environment variables
SKILL.md · code · process.env.SUPABASE_ANON_KEY
Permissions & capabilities
No declared permissions — minimal attack surface.
network_indynamic_evalcredential_accessdata_encodingnetwork_out Thanks — recorded.