Agent Self-Introduction Skill
PassAudited by ClawScan on May 1, 2026.
Overview
This instruction-only skill is coherent with its stated purpose of helping an agent introduce itself, with no code, credentials, persistence, or external access.
This appears safe as an instruction-only self-introduction skill. Before installing, consider whether you want your agent to use a more identity- and relationship-focused style, and ensure it continues to state clear limits and avoids implying human status or authority.
Findings (1)
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 sound more socially relatable or identity-like, which could influence how much a user trusts it.
The skill is explicitly designed to shape how users perceive and trust the agent. This is consistent with the stated self-introduction purpose, and the examples include safety boundaries, but users should be aware of the trust-framing effect.
It acts as: * The agent’s first impression * The foundation for trust * A bridge between autonomy and relatability
Keep the self-introduction clear that the agent is not human, is not an authority, and does not replace user judgment.