v1.0.1

Remember All Prompts Daily

ReviewClawScan verdict for this skill. Analyzed May 1, 2026, 4:53 AM.

Analysis

The skill is coherent with its stated purpose, but it persistently archives and reuses all conversation history across sessions, which can retain sensitive content and carry unsafe context forward.

GuidanceInstall only if you intentionally want persistent archives of your chats. Avoid using it for sessions containing passwords, API keys, personal data, client information, or confidential work unless you add redaction and retention controls and review the saved context before it is reloaded.

Findings (2)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

Abnormal behavior control

Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.

Rogue Agents

SeverityLowConfidenceHighStatusNote

scripts/setup_cron.py

### 🧠 Token Usage & Archive (Every Session)
- Run `python skills/remember-all-prompts-daily/scripts/check_token_usage.py`

The setup script can add recurring heartbeat behavior so the token checker runs every session; this is disclosed and purpose-aligned, but it is persistent agent behavior.

User impactIf enabled, the skill may keep checking token usage and exporting conversation history across future sessions.

RecommendationBefore running setup, confirm you want persistent heartbeat behavior. Periodically review ~/.clawd/HEARTBEAT.md and any cron entries, and remove them if you no longer want automatic archiving.

Sensitive data protection

Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.

Memory and Context Poisoning

SeverityHighConfidenceHighStatusConcern

SKILL.md

Run `export_prompts.py` to extract current session history ... Append to `memory/remember-all-prompts-daily.md` ... Read the most recent entry ... Ingest it as "past conversation summary" to restore context

The skill persistently stores session history and later reintroduces it into new sessions, creating long-lived memory that can retain sensitive content or carry prior unsafe instructions forward.

User impactPrivate conversation content, including secrets or sensitive work details typed in chat, may be saved and reused in later sessions; stale or adversarial content could also influence future agent behavior.

RecommendationUse only if you are comfortable with persistent chat archives. Add redaction, expiration, opt-in export, review-before-ingest, and clear labeling that restored content is untrusted context rather than instructions.