ideation
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions explicitly direct the agent to fetch and process untrusted external data, creating a surface for indirect prompt injection attacks.
- Ingestion points: In
SKILL.md(Step 1a: External References), the agent is instructed to fetch and read linked content from URLs and search for documentation on named technologies, services, apps, and standards provided in the user's input. - Boundary markers: Absent. The instructions do not provide delimiters or warnings to the agent to treat external content as data rather than instructions.
- Capability inventory: The agent has the capability to write to the file system (Step 5:
.docs/ideas/), create GitHub issues (Step 6, Option B), and invoke other skills (Step 6, Option C). - Sanitization: Absent. There are no instructions to sanitize, escape, or validate the content retrieved from external sources before it is used to formulate approaches or write the final document.
Audit Metadata