Intent Framed Agent

Security checks across static analysis, malware telemetry, and agentic risk

Overview

This instruction-only skill mainly asks the agent to confirm coding intent and monitor scope drift, with only minor notes around optional CLI detection, install-source verification, and possible persistent follow-up records.

This appears safe for its stated purpose. Before installing or using it, verify any external install source, be aware that it may check for the Entire CLI with a local status command, and review any later persistent self-improvement rules before saving them.

Static analysis

No static analysis findings were reported for this release.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Risk analysis

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 the user chooses to run the install command, they are trusting the referenced external package/source.

Why it was flagged

The skill documentation includes a user-directed install command that pulls from an external GitHub-style source via npx.

Skill content
npx skills add pskoett/pskoett-ai-skills/intent-framed-agent
Recommendation

Verify the repository/source and package manager behavior before running the npx install command.

What this means

The agent may execute a local command to detect whether Entire CLI is available, though the command is limited and failure is handled silently.

Why it was flagged

The skill directs the agent to run a local CLI status check when tools are available.

Skill content
When tool access is available, detect Entire at activation:

```bash
entire status 2>/dev/null
```
Recommendation

Allow this only if you are comfortable with the agent checking local Entire CLI status; otherwise deny command execution for this step.

What this means

If that follow-up skill is used, information from a coding session could influence future agent behavior.

Why it was flagged

The interoperability section suggests a later step that may turn session patterns into durable rules or memory.

Skill content
`self-improvement` (capture recurring patterns and promote durable rules)
Recommendation

Review any durable rules or memory updates before accepting them, especially if the session includes sensitive project details.