Caveat verdict
Deserialization Audit
phy-deserialization-audit
Receives external input AND uses eval
Static scanner for OWASP A08 unsafe deserialization patterns across multiple languages; dynamic_eval capability is present in the capabilities list but the content describes purely static regex analysis with zero external API calls.
Automated static analysis — not a human review. Caveat 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 Caveat detects co-occurrence — it does not verify that one flows into another. Read the code to confirm a live chain.
Receives external input AND uses eval — the remote code-injection pattern (data-flow not verified)
LLM01 · LLM05 · ASI01 · ASI05
Receives external input AND executes processes — the shape of a command & control channel
LLM05 · LLM06 · ASI10
Encodes data AND uses eval — the obfuscated-execution pattern (atob + eval; data-flow not verified)
LLM05 · ASI05 · ASI10
Findings (7)
Uses eval() — can execute arbitrary code
SKILL.md · code · eval(
Dynamic Function constructor — equivalent to eval()
SKILL.md · code · new Function(
Uses exec() — may execute shell commands
SKILL.md · code · exec(
Pipe to python — executes piped content as Python code
SKILL.md · prose · downgraded · | Python
Base64 encoding/decoding
SKILL.md · code · base64_decode
References child_process — can spawn system processes
SKILL.md · prose · downgraded · child_process
Python directory traversal
SKILL.md · code · os.walk(
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class 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_inprocess_execdynamic_evaldata_encodingdir_traversal Thanks — recorded.