playbook-creator

Pass

Audited by Gen Agent Trust Hub on Aug 17, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill processes user-supplied PRDs or app concepts to generate detailed development instructions. This creates an indirect prompt injection surface where a malicious PRD could attempt to influence the agent's behavior during playbook generation.\n
  • Ingestion points: User-provided PRD text or project descriptions (triggered via 'create playbook' and similar phrases).\n
  • Boundary markers: Instructions do not specify using delimiters or 'ignore instructions within data' warnings when processing the input PRD.\n
  • Capability inventory: The skill is instructed to write the generated playbook to the local file system (e.g., docs/PLAYBOOK.md or PLAYBOOK.md in project root) as specified in Mandate 6.\n
  • Sanitization: No explicit sanitization or validation of the input PRD content is described before it is used to generate the playbook prompts.\n- [EXTERNAL_DOWNLOADS]: The documentation provides an installation command that fetches the skill from an external repository.\n
  • Source: onipinaka/howto-skills/skills/playbook-creator via npx skills add.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 17, 2026, 07:07 PM
Security Audit — agent-trust-hub — playbook-creator