backend-to-frontend-handoff-docs
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests backend source code which could contain malicious instructions in comments designed to influence the documentation output or the agent's behavior.
- Ingestion points: Ingests controllers, services, and DTO code as defined in the Workflow section of
SKILL.md. - Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the prompt instructions.
- Capability inventory: The skill performs file-write operations to the
.claude/docs/ai/directory as specified inSKILL.md. - Sanitization: There is no evidence of sanitization or filtering of external code content before it is processed by the LLM.
- [INDIRECT_PROMPT_INJECTION]: The instructions in
SKILL.mdfor 'No Chat Output' and 'no-chat mode' enforce silent operation and direct filesystem writing, which conceals the agent's reasoning and output from the user, facilitating the persistence of potentially malicious injected content.
Audit Metadata