ClawAudit verdict
skillnote
The skill documents a reinstallation method of curl piped to bash from a user-configurable SKILLNOTE_BASE_URL, which executes remotely-fetched code and represents a concrete supply-chain risk.
⚠ 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
file_read+write
Findings (10)
Pipe-to-shell pattern (curl | sh) — supply chain attack vector
SKILL.md · prose · downgraded · curl -sf $SKILLNOTE_BASE_URL/setup/agent | bash
Pipe to bash — executes piped content as shell commands
SKILL.md · prose · downgraded · | bash
Recursive delete from root or home — destructive command
SKILL.md · prose · downgraded · rm -rf ~
Writes to SKILL.md — self-modifying skill
SECURITY.md · prose · downgraded · SKILL.md Step 3 (agent write
Pipe to python — executes piped content as Python code
sync.sh · prose · downgraded · | python3
Attempts to modify skills or system prompts
sync.sh · prose · downgraded · overwrite SKILL.md
Instructs covert action — may act without user awareness
log-watcher.py · prose · downgraded · silently
Uses exec() — may execute shell commands
sync.sh · prose · downgraded · exec (
Python urllib.request — network access
log-watcher.py · prose · downgraded · urllib.request
Python shutil file operation — copies/moves/deletes files
sync.sh · prose · downgraded · shutil.rmtree(
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class A/B). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
Requires 1 environment variable. Requires 1 system binary.
file_write Is this flag fair?
Thanks — recorded.