pp-jira

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill tells users/agents to run commands like "jira-pp-cli auth set-token YOUR_TOKEN_HERE" (and similar CLI flags/sinks) which requires embedding API tokens/credentials verbatim into generated commands/outputs, creating an exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly instructs the agent to run jira-pp-cli commands that fetch and parse user-generated Jira content (e.g., "jira-pp-cli comment", "jira-pp-cli issue get", "jira-pp-cli attachment get-content") and describes Agent Mode and parsing of .results, so the agent will ingest untrusted third-party (user-generated) content from a Jira instance as part of its workflow, which could contain instructions that influence subsequent actions.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill instructs runtime installation that fetches and executes remote code (required dependency) via npx @mvanhorn/printing-press (npm) and go install github.com/mvanhorn/printing-press-library/library/project-management/jira/cmd/jira-pp-cli@latest, so the github.com URL and the npm package are runtime external dependencies that execute remote code.