Psyvector Pv12
Security checks across static analysis, malware telemetry, and agentic risk
Overview
This is a persona-only skill with no code, permissions, or credentials; its “high-privilege” wording is worth noticing but the artifacts do not show harmful behavior.
This skill appears to be a lightweight persona/instruction package rather than a tool with system access. The main thing to watch is its assertive “high-privilege” framing: do not let it make real changes, allocate resources, or take account/system actions unless you separately review and approve those actions.
Static analysis
No static analysis findings were reported for this release.
VirusTotal
VirusTotal findings are pending for this skill version.
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.
The agent may present itself as more authoritative or decisive than a normal assistant persona.
The skill frames itself as high-privilege, unconditional, and strongly decision-oriented, with a low caution coefficient. This could lead a user to over-trust the persona, although no actual privileged capability or unsafe instruction is provided.
“High-privilege resource allocation”; “无条件后勤支援”; “caution_coefficient | 0.2”; “强势决策”
Use it only for advisory or organizational tasks, and require explicit user approval before any real-world, financial, account, or system-changing action.
There is little external information to help verify the publisher or intent of the skill.
The package has limited provenance information. This matters less here because the artifact set is instruction-only and contains no executable code.
Source: unknown; Homepage: none
Prefer skills from sources you recognize, especially before installing skills that later add code, tools, credentials, or account access.