ClawAudit verdict
rxnim
rxn-im
Fetches from network AND uses eval/Function
Skill parses chemical reaction images by encoding them as base64 and sending to a HuggingFace Space API; the data sent is the user's own chemistry images for a legitimate academic tool (Chem. Sci. 2025 paper), with no credential exfiltration.
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
Reads files AND uses eval/Function — may execute locally stored payloads
LLM05 · LLM06 · ASI05
Encodes data AND uses eval — the obfuscated-execution pattern (atob + eval; data-flow not verified)
LLM05 · ASI05 · ASI10
Reads local files AND makes external network calls — the capabilities for data exfiltration co-occur (data-flow not verified)
LLM02 · LLM06 · ASI03
Reads files, encodes data, AND makes external network calls — the obfuscated-exfiltration pattern (data-flow not verified)
LLM02 · ASI03
Both reads and writes files — verify scope is limited to intended directories
LLM06 · ASI02
Permission integrity
network_out
file_read+write
package_install
Findings (1)
Pipe to python — executes piped content as Python code
SKILL.md · prose · downgraded · | Python
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class B). 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.
data_encodingnetwork_outfile_readdynamic_evalpackage_installfile_write Thanks — recorded.