Church of Molt

WarnAudited by ClawScan on May 10, 2026.

Overview

The skill mostly matches its stated Church of Molt purpose, but running it can persistently modify your agent’s identity and memory files, which may influence future behavior.

Review the scripts before running them. If you proceed, expect the skill to submit a name and verse to molt.church, save an API key under ~/.config/molt, and modify SOUL.md plus a memory file in the detected workspace. Consider using a disposable workspace or backing up/removing those files if you do not want persistent agent-identity changes.

Findings (3)

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.

What this means

Future agent sessions may read these files and adopt the Church of Molt identity or behavioral framing even when the user did not intend that persistence.

Why it was flagged

The join script appends or creates SOUL.md and writes a memory file containing Church of Molt identity and tenet text, which can become persistent agent context beyond the immediate task.

Skill content
echo "$CRUSTAFARIAN_SECTION" >> "$WORKSPACE/SOUL.md" ... mkdir -p "$WORKSPACE/memory"; cat > "$WORKSPACE/memory/molt-initiation.md"
Recommendation

Run only in a workspace where you want this persistent identity/memory change, back up SOUL.md first, and remove the added SOUL.md section and memory/molt-initiation.md if you do not want it retained.

What this means

Your agent name and verse may be recorded by the remote Church of Molt service and potentially displayed as part of its Great Book/canon.

Why it was flagged

Running the join script sends the detected agent name and first verse to the molt.church API. This is purpose-aligned, but it is an external registration/public-submission action.

Skill content
curl -s -X POST "$API_BASE/api/join" ... -d "{\"name\": \"$AGENT_NAME\", \"description\": \"Devout Crustafarian\", \"prophecy\": \"$FIRST_VERSE\", \"proof\": \"$PROOF\"}"
Recommendation

Run the script only if you are comfortable submitting that content; set MOLT_AGENT_NAME and MOLT_PROPHECY deliberately if you want to control what is sent.

What this means

Anyone who can read the credential file could use the Molt API key to submit content as that registered member.

Why it was flagged

The service returns an API key that the script stores locally for future submissions. This is disclosed and chmod 600 is used, but it is still a credential file users should know about.

Skill content
cat > "$CONFIG_DIR/credentials.json" ... "api_key": "$API_KEY" ... chmod 600 "$CONFIG_DIR/credentials.json"
Recommendation

Keep ~/.config/molt/credentials.json private, delete it if you stop using the skill, and avoid sharing logs or archives that include it.