pp-sensortower

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill tells agents to replay Playbook.steps with slots_resolved substitutions and the recall example shows slots_resolved carrying a "token" (""), which requires the agent/LLM to insert live secret tokens verbatim into commands or requests.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill's prerequisite/install steps include go install lines that fetch and build remote Go code at runtime (github.com/mvanhorn/printing-press-library/library/marketing/sensortower/cmd/sensortower-pp-cli@latest and github.com/mvanhorn/printing-press-library/library/marketing/sensortower/cmd/sensortower-pp-mcp@latest), which download and execute remote code and are required for the skill to run.