do-effect-service-design
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read and prioritize rules from external project files such as
AGENTS.md, architecture docs, andreferences/AUDIT.md. This creates a vulnerability where malicious instructions embedded in those files could influence the agent's design decisions or audit results.\n - Ingestion points: Steps 1 and 2 in
SKILL.mddirect the agent to readAGENTS.md, architecture docs, andreferences/AUDIT.md.\n - Boundary markers: There are no instructions to treat external data as untrusted or to use delimiters to prevent command injection from those files.\n
- Capability inventory: The skill enables the agent to refactor modules, design new services, and generate audit reports based on the ingested content.\n
- Sanitization: The skill does not mention any validation or filtering of the content read from the external files.
Audit Metadata