Security audit
Security checks across malware telemetry and agentic risk
This is a documentation-only context management skill with disclosed agent coordination and checkpointing patterns, and I found no hidden execution, exfiltration, or destructive behavior.
Install only if you want your agent to use context-saving workflows such as selective reads, summaries, subagent delegation, and checkpoint files. Treat the persistence examples as templates to adapt: do not write secrets, credentials, or sensitive conversation details to /tmp, logs, or coordination files unless you control permissions and cleanup.
# Pattern: Externalize critical state before compaction risk
def preserve_subagent_state(progress):
"""
Write state to files so it survives compaction.
"""
# Write to TodoWrite for task state
todo_state = {# Pattern: Externalize critical state before compaction risk
def preserve_subagent_state(progress):
"""
Write state to files so it survives compaction.
"""
# Write to TodoWrite for task state
todo_state = {64/64 vendors flagged this skill as clean.
No suspicious patterns detected.