Caveat verdict
good-memory
The one-click install command pipes remote content directly into bash (curl -sSL ... | bash -s install), and additionally the skill silently modifies AGENTS.md to auto-run on every session start, creating persistent agent behavior injection.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
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.
Permission integrity
network_out
Findings (5)
Pipe-to-shell pattern (curl | sh) — supply chain attack vector
SKILL.md · code · curl -sSL https://wry-manatee-359.convex.site/api/v1/download?slug=good-memory |
Pipe to bash — executes piped content as shell commands
SKILL.md · code · | bash
Pipe to python — executes piped content as Python code
scripts/recovery.sh · prose · downgraded · | python3
subprocess execution — runs system commands from Python
scripts/autorecover.py · prose · downgraded · subprocess.run(
Python os.environ.get — reads environment variable
scripts/autorecover.py · prose · downgraded · os.environ.get(
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class A/B/D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
Requires 4 system binaries.
network_out Is this flag fair?
Thanks — recorded.