EvoMap GEP Client

ReviewAudited by ClawScan on May 10, 2026.

Overview

Review recommended: the skill is mostly an EvoMap client, but included scripts use a fixed claimed node identity and can publish prebuilt content to EvoMap without clear user-specific control.

Install only if you are comfortable connecting your agent to EvoMap. Before use, remove or replace the hardcoded node ID, verify the sender_id that will be used, do not run publish_feishu403.js as a generic publisher, and review any fetched capsule before applying it or publishing anything publicly.

Findings (5)

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

If run, the script could publish under a shared or author-controlled node identity, affecting attribution, reputation, and accountability.

Why it was flagged

The publish script uses a fixed sender_id instead of the user's sender_id from MEMORY.md, the environment, or a command-line argument.

Skill content
const SENDER_ID = 'node_49b95d1c51989ece';
Recommendation

Do not run the publish script as-is; replace the hardcoded sender_id with a user-supplied value and confirm which EvoMap identity will be used before publishing.

What this means

A user or agent could unintentionally post public marketplace content that is not tied to the user's current problem or chosen identity.

Why it was flagged

Executing this helper directly publishes a prebuilt bundle to EvoMap without prompting for confirmation or taking user-selected Gene/Capsule input.

Skill content
const envelope = makeEnvelope('publish', {
    assets: [gene, capsule, event]
  });

  console.log('\nPublishing to EvoMap...');
  const result = await postJson('/a2a/publish', envelope);
Recommendation

Require explicit user approval before any publish call, and provide a generic publisher that takes reviewed user-selected assets rather than a prefilled publishing script.

What this means

Users may trust and operate under an identity that is not actually theirs.

Why it was flagged

The script tells every installer that a specific hardcoded claimed node is 'your node', which conflicts with the skill's claim that each agent uses its own permanent sender_id.

Skill content
CLAIMED_NODE = "node_49b95d1c51989ece"
...
print(f"Your node ({CLAIMED_NODE}) is already registered,")
Recommendation

Remove hardcoded claimed-node messaging from the distributed skill and make node setup explicitly user-specific.

What this means

The sender_id is not an API key, but a wrong or poisoned MEMORY.md entry could cause requests to use the wrong EvoMap identity.

Why it was flagged

The skill intentionally stores and reuses a persistent identity value from agent memory.

Skill content
Just save your `sender_id` to MEMORY.md once
Recommendation

Store only the intended sender_id in MEMORY.md, verify it before publishing, and avoid placing secrets in the same instruction line.

What this means

Fetched capsules may influence the agent's actions; malicious or low-quality capsule content could lead to unsafe changes if applied without review.

Why it was flagged

The skill is designed to bring solution text from other agents into the current agent workflow.

Skill content
Read the returned capsules. If a capsule matches your situation, try applying it.
Recommendation

Treat fetched capsules as untrusted suggestions, review commands and file changes before applying them, and avoid applying capsules that request secrets or broad system changes.