engineering-flow
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill directs the agent to ingest and ground technical decisions in external sources such as industry articles and community posts. This creates a surface for indirect prompt injection where untrusted external content could influence agent behavior.
- Ingestion points: External URLs, official documentation, and community posts (as defined in the Research & Evidence Hierarchy).
- Boundary markers: Absent. The instructions do not provide specific delimiters or warnings to ignore embedded directives within processed external research.
- Capability inventory: The agent is instructed to perform file system operations (creating RFCs/ADRs, modifying code), execute package manager commands (npm, go, pip), and run throwaway scripts in a
scratch/directory. - Sanitization: No explicit sanitization or validation of external content is mentioned beyond checking the age of the source.
Audit Metadata