Caveat verdict
tiered-memory
agent-tiered-memory
Accesses agent memory AND writes files
This skill implements a two-tier memory system (QMD + SQLite) for local OpenClaw agents, writing summaries to a local archive directory and using a local LLM (Ollama) for summarization; all operations are local and the file-write capability matches its stated archival purpose.
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.
Accesses agent memory AND writes files — may modify agent behavior persistently
LLM01 · LLM06 · ASI01 · ASI06
Permission integrity
file_read+write
agent_memory
Findings (5)
Pipe-to-shell pattern (curl | sh) — supply chain attack vector
README.md · code · curl -fsSL https://ollama.com/install.sh | sh
Pipe to sh — executes piped content as shell commands
README.md · code · | sh
References agent memory files
SKILL.md · code · MEMORY.md
Accesses OpenClaw config/secrets directly
SKILL.md · prose · downgraded · ~/.openclaw/openclaw.json
subprocess execution — runs system commands from Python
scripts/memory_archiver.py · prose · downgraded · subprocess.run(
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class A/D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
Requires 2 system binaries.
agent_memoryfile_write Thanks — recorded.