Capability Awareness System
PassAudited by ClawScan on May 10, 2026.
Overview
This instruction-only skill is coherently focused on helping agents discover and read installed skill documentation, with no code, credentials, or automatic execution shown.
This appears safe as an instruction-only skill, but it works by making the agent consult and follow other installed skill documentation. Review the skills in your workspace and verify the external GitHub repository if you choose to use the manual clone instructions.
Findings (2)
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.
The agent may change how it responds based on instructions in other installed skills.
The skill intentionally makes installed skill documentation actionable for the agent. This is the core purpose, but it means untrusted or poorly written SKILL.md files could influence agent behavior.
If exactly one skill clearly applies: read its SKILL.md at <location> with `read`, then follow it.
Only install or expose skills you trust, and review other SKILL.md files before letting the agent rely on them.
If the external repository changes or contains additional files, those contents may differ from the artifacts reviewed here.
The documentation includes a user-directed clone from an external GitHub repository, while the reviewed package itself contains only markdown files and no install spec.
git clone https://github.com/pfaria32/openclaw-capability-awareness.git projects/capability-awareness-system
Prefer the ClawHub install path when possible, or inspect the GitHub repository before cloning it into the workspace.