okr
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user data (SCOPE, DIRECTION, CONTEXT) and interpolates it into generated markdown documents and subagent prompts.
- Ingestion points: User-provided inputs for scope, direction, and context are used throughout the facilitation cycle in SKILL.md.
- Boundary markers: The instructions do not specify the use of clear delimiters or "ignore embedded instructions" warnings to separate user data from the agent's internal logic during processing.
- Capability inventory: The skill uses file-writing capabilities to save the OKR document in the working directory using a filename derived from user input (SKILL.md).
- Sanitization: There are no explicit instructions for sanitizing or validating user-provided strings before they are used in file operations or prompt construction.
Audit Metadata