Agent Intelligence Network Scan
ReviewAudited by ClawScan on May 10, 2026.
Overview
This skill has no executable implementation but makes strong trust, threat, and investment-safety claims, so users should review it carefully before relying on its ratings.
Install only if you understand that this package appears to be documentation-only. Do not rely on its reputation, threat, or investment guidance until the missing engine, MCP tools, backend source, data provenance, and cache update process are independently verified.
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.
A user or agent could over-trust unsupported reputation labels and make business, collaboration, or investment decisions based on ratings that cannot be verified from the provided package.
The skill presents its scores as safety and trust guidance for potentially high-impact collaboration or investment decisions, but the supplied artifact set does not include the claimed implementation or verifiable data source.
Use when evaluating agent trustworthiness ... or making collaboration/investment decisions based on agent quality metrics. ... 80-100: Verified leader - collaborate with confidence ... 60-79: Established - safe to engage
Treat the ratings as unverified until the provider supplies a working implementation, data provenance, backend identity, and clear limitations for how scores should be used.
If a user tries to make the skill functional, they may need to locate and run unreviewed external code that was not included in this security review.
The documentation references helper scripts, MCP tools, and external collectors that are not included in the provided file manifest, creating an incomplete provenance and review context.
Core Engine (`scripts/query_engine.js`) ... MCP Tools (`scripts/mcp_tools.json`) ... Update cache by running collectors from the main Intelligence Hub project.
Do not run separately obtained collectors or scripts unless their source, integrity, and permissions have been reviewed.
Old or manipulated cache data could cause the agent to recommend or warn against other agents incorrectly.
The skill describes persistent local reputation and threat-intelligence caches that could influence future decisions if stale, incomplete, or poisoned.
Cache files go to `~/.cache/agent-intelligence/`: `agents.json` ... `threats.json` ... `leaderboards.json` ... `trends.json`
Verify cache provenance, freshness, and update controls before relying on locally cached reputation or threat results.