ClawAudit verdict
context-restore
Accesses agent memory AND writes files
Session context restoration skill that reads local compressed context files and writes formatted summaries; all file operations and cron scheduling are consistent with the stated cross-session resumption purpose.
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.
Accesses agent memory AND writes files — may modify agent behavior persistently
LLM01 · LLM06 · ASI01 · ASI06
Permission integrity
file_read+write
agent_memory
Findings (6)
Pipe to python — executes piped content as Python code
docs/USAGE.md · code · | python
References agent memory files
SKILL.md · code · MEMORY.md
Popular HTTP library — network access
docs/error_handling_report.md · code · got
subprocess execution — runs system commands from Python
tests/test_full_integration.py · prose · downgraded · subprocess.run(
Python os.environ.get — reads environment variable
UX_EVALUATION_REPORT.md · code · os.environ.get(
Python shutil file operation — copies/moves/deletes files
tests/test_phase3_auto_cron.py · prose · downgraded · shutil.copy(
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.
agent_memoryfile_write Thanks — recorded.