pp-aol-puglia

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill includes an explicit example that places an OAuth bearer token directly on the command line ("aol-puglia-pp-cli auth set-token YOUR_TOKEN_HERE"), which would require the LLM/agent to handle and emit secret values verbatim (an exfiltration risk), even though an env-var alternative is mentioned.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). SKILL.md describes using the first-party aol-puglia-pp-cli to fetch/search content from the public “Albo Pretorio Online” (sanita.puglia.it) via its atti search/get-atto/download-allegato commands, meaning runtime free text from outsider-authored published items can be ingested when the agent searches and retrieves those records/allegati.