Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
heursistic
v1.0.0Master reference for 88 psychological heuristics — the complete leverage list for sales, copywriting, offer design, cold outreach, objection handling, and pe...
⭐ 0· 53·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
medium confidencePurpose & Capability
Name/description match the actual content (a reference of persuasion heuristics). There are no requested binaries, env vars, or installs that don't belong to this purpose.
Instruction Scope
The SKILL.md tells the agent to 'Always trigger... without exception' whenever a task involves influencing humans, which is unusually broad and grants the skill behavioral scope beyond its registry flags. It also instructs the agent to 'Load the reference file' at /references/heuristics-full.md, but that file is not present in the package (skill is instruction-only). These are runtime/instruction inconsistencies and grant wide discretion to an invoking agent.
Install Mechanism
There is no install spec or code to download; this is instruction-only, so nothing is written to disk by an installer.
Credentials
The skill requires no environment variables, credentials, or config paths — consistent with a static reference skill.
Persistence & Privilege
Registry flags are default (always:false, agent invocation allowed). The SKILL.md's insistence that the skill be consulted 'every time, without exception' is inconsistent with the lack of always:true in metadata; this is a behavioral concern (broad invocation) but not an explicit privilege escalation in the registry.
What to consider before installing
This skill is primarily a text reference for persuasion heuristics and does not request credentials or install anything — that's good. However: (1) the runtime instructions instruct the agent to always consult this skill 'without exception,' which is unusually broad; consider whether you want the agent to be allowed to call it autonomously for all tasks that 'involve influencing humans.' (2) The SKILL.md refers to /references/heuristics-full.md, but that file isn't included — ask the publisher to provide the referenced resource or remove the instruction to 'load' it. (3) Because the content is about persuasion/manipulation, review it for ethical and legal appropriateness for your use cases. If you decide to install: restrict autonomous invocation or require user confirmation for sensitive actions, and request the missing reference file or a clearer scope statement from the author before trusting automatic, frequent invocation.Like a lobster shell, security has layers — review code before you run it.
latestvk97dab7yg3v4aydxyf99q085e583ke75
License
MIT-0
Free to use, modify, and redistribute. No attribution required.