pp-boardgamegeek

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill instructs storing a bearer token by running a CLI command that takes the token as a literal argument (boardgamegeek-pp-cli auth set-token YOUR_TOKEN_HERE) and also documents that an Authorization: Bearer header is required, which would force an agent to handle or emit the secret verbatim if it follows that example instead of using env vars or the CLI's internal auth mechanisms securely.

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

• Third-party content exposure detected (low risk: 0.10). SKILL runtime path only triggers the first-party BoardGameGeek XMLAPI2 via the boardgamegeek-pp-cli CLI with explicit command arguments (e.g., searches, thing, hot, user, collection), and there is no workflow step that reads outsider-authored free text from a user-submitted feed/inbox/issue body without the agent selecting specific items.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill includes go install commands that fetch and build remote Go modules at runtime (e.g., github.com/mvanhorn/printing-press-library/library/media-and-entertainment/boardgamegeek/cmd/boardgamegeek-pp-cli@latest and github.com/mvanhorn/printing-press-library/library/media-and-entertainment/boardgamegeek/cmd/boardgamegeek-pp-mcp@latest), which execute remote code as part of the optional/installed workflow.