architectural-programme-brief
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill is comprised entirely of Markdown files providing instructions and templates for the AI agent. There are no executable scripts, shell commands, or binaries included.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input (client notes and project details) to generate a brief.
- Ingestion points: User inputs are requested in
SKILL.mdunder the 'Required Inputs' section. - Boundary markers: The template in
SKILL.mddoes not utilize specific delimiters for user-provided data. - Capability inventory: The skill does not use any tools, perform network operations, or execute code.
- Sanitization: No input validation or filtering is specified.
- [SAFE]: No malicious patterns such as data exfiltration, obfuscation, or persistence mechanisms were found. The skill operates within a safe text-only interaction model.
Audit Metadata