brainstorm-okrs
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions require the agent to ingest and process external data, creating a potential surface for indirect prompt injection attacks.
- Ingestion points: In SKILL.md, the agent is directed to read company objectives, strategic documents, and team context provided as files by the user, as well as information gathered from web searches.
- Boundary markers: The instructions do not define specific delimiters or "ignore instructions" markers to separate user-provided data from the skill's logic.
- Capability inventory: The skill leverages web search tools and file system write operations (saving OKR sets as markdown files).
- Sanitization: There are no defined procedures for validating or sanitizing the content retrieved from external files or web search results.
Audit Metadata