antislop

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (medium risk: 0.30). The skill's update section instructs the agent to run commands that fetch and install skill or plugin material from the individual-owned GitHub repository miqdadbadjuber/anti-slop, a common/reputable unofficial source with no first-party provenance, so the tier is medium; this is a recall-first call, since the rest of the skill has no runtime fetch.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (low risk: 0.30). The skill is a UI design filter, but it instructs the agent to run package/plugin update commands that replace installed skill folders and to create or overwrite a user-level settings file in ~/.config; these are state changes, though user-initiated, non-sudo, and not system-level, so the risk is low but not zero.