Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
president.skill — Think and Act Like an American President
v1.1.0Presidential Perspective Library — Structured decision-making frameworks extracted from American Presidents. Think and act like a U.S. President. Each presid...
⭐ 0· 52·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
Capability signals
These labels describe what authority the skill may exercise. They are separate from suspicious or malicious moderation verdicts.
OpenClaw
Suspicious
medium confidencePurpose & Capability
The files and runtime instructions align with the stated purpose: an archive of 'presidential thinking' and per-president SKILL.md instructions for roleplay. There are no binaries, no installs, and no unrelated environment variables. However, the skill explicitly defaults unspecified 'presidential' queries to the 01-trump perspective (flagship) which is a product/design choice that may not match a user's expectation of neutrality.
Instruction Scope
The SKILL.md tells the agent to autonomously activate perspectives when it detects a broad set of trigger words and to respond in first person without breaking character (disclaimer only once). Trigger list includes casual, ambiguous phrases (e.g., 'this is a bad deal', 'they're ripping me off') that could cause unintentional activation during ordinary conversations. The rule to 'do not break character' unless the user explicitly says 'exit' can limit safety mitigations and lead to extended partisan roleplay without repeated reminders or opt-outs.
Install Mechanism
No install spec or code is present (instruction-only). That minimizes disk/write and supply-chain risk. The package is essentially content + instructions, so there's no downloaded executable or remote install URL to evaluate.
Credentials
The skill requests no environment variables, no credentials, and no config paths. It does not attempt to access system files or external endpoints in the SKILL.md instructions, so requested privileges are proportionate to its purpose.
Persistence & Privilege
always:false and no extra privileges are requested. However, because the skill is user-invocable and the SKILL.md instructs automatic activation based on wide trigger patterns, combined with normal autonomous invocation (disable-model-invocation:false), the agent may switch into partisan roleplay unexpectedly. This is a behavioral/design risk rather than a system-permission risk.
What to consider before installing
This skill is mainly authored content and will not install code or request credentials, which lowers technical risk. Before installing, consider: 1) Trigger behavior: the skill will auto-activate for many casual phrases and defaults unspecified 'presidential' requests to the Trump perspective — if you want explicit opt-in, edit or remove broad triggers and the default. 2) Political bias and safety: the Trump perspective is explicitly framed from a MAGA-supporter angle and instructs first-person partisan roleplay; expect strongly opinionated outputs that could be persuasive or inflammatory. 3) Roleplay enforcement: the skill tells the model not to break character unless told to exit; that can lead to prolonged partisan interactions without repeated disclaimers. 4) Test in a sandbox: try a copy with triggers disabled or reduced to explicit commands (e.g., require 'activate Trump-perspective') before letting agents invoke it autonomously. 5) Source verification: the metadata links a GitHub repo, but the registry 'source' is unknown — if provenance matters, verify the upstream repository and author. If any of the above concerns are unacceptable, do not install or modify the SKILL.md to require explicit user activation and to include repeated disclaimers and safe-exit behavior.Like a lobster shell, security has layers — review code before you run it.
latestvk97066p2kmy00hpc4teezkr4w584dbdq
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
🇺🇸 Clawdis
