Agent Collaboration Protocol

AdvisoryAudited by Static analysis on May 9, 2026.

Overview

No suspicious patterns detected.

Findings (0)

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

Generated or copied code could break an application or introduce defects if merged or activated without human review.

Why it was flagged

The skill intentionally has subagents create application code and later instructs activation/integration. This is core to the build workflow, but it can affect a real project if used without review.

Skill content
Write all backend code to {ABSOLUTE_BUILD_DIR}/backend/ ... Write all frontend code to {ABSOLUTE_BUILD_DIR}/frontend/ ... Step 5: Deploy & Activate
Recommendation

Use a branch or sandbox, keep the build directory scoped, inspect diffs, run tests, and manually approve any copy/deploy step.

What this means

Information placed in the shared spec or logs may be visible to multiple spawned agents and may influence their work.

Why it was flagged

The skill's intended mechanism is inter-agent delegation through a shared filesystem workspace. The workflow is disclosed and scoped, but users should understand that multiple agents will read and write shared artifacts.

Skill content
Three roles collaborate through a shared workspace ... Spawn two subagents with `sessions_spawn`
Recommendation

Only put task-relevant information in the shared workspace, avoid secrets, and verify each subagent's output before trusting it.

What this means

If a user pastes real credentials into the shared contract or logs, those secrets could persist in project files and be exposed to other agents.

Why it was flagged

The templates include authentication scheme fields. This is expected for backend/frontend integration, but real tokens or cookies should not be written into shared specs or logs.

Skill content
| Auth Scheme | Bearer JWT / Session cookie / None |
Recommendation

Use placeholders for tokens, document auth flow without real secrets, and redact any credentials from generated files or logs.

What this means

Running the helper will create or modify local project files, including a .gitignore if one does not already exist.

Why it was flagged

A shell helper is included and can write files in a chosen project directory. It is not automatically run by an install spec, and the visible commands are simple workspace initialization steps.

Skill content
Usage: ./init_collab.sh /path/to/project ... mkdir -p "$SHARED_DIR" ... cat > "$PROJECT_DIR/.gitignore"
Recommendation

Review the script before running it and execute it only against the intended project path.