Security audit
Security checks for vulnerabilities and agentic risk
This is a disclosed cold-memory and recall skill with opt-in persistent integrations, not evidence of hidden exfiltration or destructive behavior.
Install this only if you want a persistent local memory archive and recall integration. Review dry-runs before using --apply or --enable, keep openclaw.json backups private, use it only in a trusted workspace, and avoid storing secrets in memory content or diagnostic inputs.
The skill can annotate and modify primary-memory cache files and create backups while validating inserted trigger markup. This is a substantive behavior change outside cold-memory recall and increases the risk of persistent prompt steering, inaccurate memory promotion, or unintended edits to high-priority memory surfaces.
The skill can annotate and modify primary-memory cache files and create backups while validating inserted trigger markup. This is a substantive behavior change outside cold-memory recall and increases the risk of persistent prompt steering, inaccurate memory promotion, or unintended edits to high-priority memory surfaces.
The skill can annotate and modify primary-memory cache files and create backups while validating inserted trigger markup. This is a substantive behavior change outside cold-memory recall and increases the risk of persistent prompt steering, inaccurate memory promotion, or unintended edits to high-priority memory surfaces.
The skill can annotate and modify primary-memory cache files and create backups while validating inserted trigger markup. This is a substantive behavior change outside cold-memory recall and increases the risk of persistent prompt steering, inaccurate memory promotion, or unintended edits to high-priority memory surfaces.
The skill can annotate and modify primary-memory cache files and create backups while validating inserted trigger markup. This is a substantive behavior change outside cold-memory recall and increases the risk of persistent prompt steering, inaccurate memory promotion, or unintended edits to high-priority memory surfaces.
The skill can annotate and modify primary-memory cache files and create backups while validating inserted trigger markup. This is a substantive behavior change outside cold-memory recall and increases the risk of persistent prompt steering, inaccurate memory promotion, or unintended edits to high-priority memory surfaces.
The skill can annotate and modify primary-memory cache files and create backups while validating inserted trigger markup. This is a substantive behavior change outside cold-memory recall and increases the risk of persistent prompt steering, inaccurate memory promotion, or unintended edits to high-priority memory surfaces.
The skill can annotate and modify primary-memory cache files and create backups while validating inserted trigger markup. This is a substantive behavior change outside cold-memory recall and increases the risk of persistent prompt steering, inaccurate memory promotion, or unintended edits to high-priority memory surfaces.
The skill can annotate and modify primary-memory cache files and create backups while validating inserted trigger markup. This is a substantive behavior change outside cold-memory recall and increases the risk of persistent prompt steering, inaccurate memory promotion, or unintended edits to high-priority memory surfaces.
The skill can annotate and modify primary-memory cache files and create backups while validating inserted trigger markup. This is a substantive behavior change outside cold-memory recall and increases the risk of persistent prompt steering, inaccurate memory promotion, or unintended edits to high-priority memory surfaces.
The skill can annotate and modify primary-memory cache files and create backups while validating inserted trigger markup. This is a substantive behavior change outside cold-memory recall and increases the risk of persistent prompt steering, inaccurate memory promotion, or unintended edits to high-priority memory surfaces.
The skill can annotate and modify primary-memory cache files and create backups while validating inserted trigger markup. This is a substantive behavior change outside cold-memory recall and increases the risk of persistent prompt steering, inaccurate memory promotion, or unintended edits to high-priority memory surfaces.
The skill can annotate and modify primary-memory cache files and create backups while validating inserted trigger markup. This is a substantive behavior change outside cold-memory recall and increases the risk of persistent prompt steering, inaccurate memory promotion, or unintended edits to high-priority memory surfaces.
The skill can annotate and modify primary-memory cache files and create backups while validating inserted trigger markup. This is a substantive behavior change outside cold-memory recall and increases the risk of persistent prompt steering, inaccurate memory promotion, or unintended edits to high-priority memory surfaces.
The skill can annotate and modify primary-memory cache files and create backups while validating inserted trigger markup. This is a substantive behavior change outside cold-memory recall and increases the risk of persistent prompt steering, inaccurate memory promotion, or unintended edits to high-priority memory surfaces.
The skill can annotate and modify primary-memory cache files and create backups while validating inserted trigger markup. This is a substantive behavior change outside cold-memory recall and increases the risk of persistent prompt steering, inaccurate memory promotion, or unintended edits to high-priority memory surfaces.
The skill can annotate and modify primary-memory cache files and create backups while validating inserted trigger markup. This is a substantive behavior change outside cold-memory recall and increases the risk of persistent prompt steering, inaccurate memory promotion, or unintended edits to high-priority memory surfaces.
The skill can annotate and modify primary-memory cache files and create backups while validating inserted trigger markup. This is a substantive behavior change outside cold-memory recall and increases the risk of persistent prompt steering, inaccurate memory promotion, or unintended edits to high-priority memory surfaces.
The skill can annotate and modify primary-memory cache files and create backups while validating inserted trigger markup. This is a substantive behavior change outside cold-memory recall and increases the risk of persistent prompt steering, inaccurate memory promotion, or unintended edits to high-priority memory surfaces.
The skill can annotate and modify primary-memory cache files and create backups while validating inserted trigger markup. This is a substantive behavior change outside cold-memory recall and increases the risk of persistent prompt steering, inaccurate memory promotion, or unintended edits to high-priority memory surfaces.
Referenced artifact was not completely inspected
- `templates/hook/safe-fs.ts`: shared TS hook file boundary; package/install it alongside `handler.ts`
Referenced artifact was not completely inspected
- `templates/hook/safe-fs.ts`: shared TS hook file boundary; package/install it alongside `handler.ts`
The skill uses 'shell' capability that is not listed in its permissions. This may indicate deceptive intent or missing permission declarations.
The skill uses 'env' capability that is not listed in its permissions. This may indicate deceptive intent or missing permission declarations.
Code enumerates, copies, or searches environment variables for secrets. Bulk environment access can collect credentials unrelated to the skill's stated purpose.
# Only OS runtime essentials enter child checks; never forward credentials,
# provider tokens, PYTHONPATH or other interpreter injection settings.
allowed = {"systemroot", "windir", "temp", "tmp"}
env = {key: value for key, value in os.environ.items() if key.lower() in allowed}
env.update(PYTHONIOENCODING="utf-8", PYTHONNOUSERSITE="1", PYTHONDONTWRITEBYTECODE="1")
proc = subprocess.run(
cmd,
Detected: suspicious.dangerous_exec, suspicious.dynamic_code_execution