delegation-prompt-crafter
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface because it is designed to ingest user-supplied information and interpolate it into structured prompts for other agents.
- Ingestion points: Business goals, current state descriptions, and key constraints are ingested from user inputs into the delegation templates.
- Boundary markers: The templates use markdown headers to separate sections but do not include explicit instructions or delimiters to warn downstream agents to ignore embedded instructions within the user data.
- Capability inventory: While the skill itself contains no code, it is intended to trigger specialist agents (such as cto-architect) that likely possess significant operational capabilities or tool access.
- Sanitization: There is no implementation of input validation, escaping, or sanitization of user-provided content before it is placed into the prompts.
- [NO_CODE]: The skill consists entirely of markdown documentation and delegation templates, with no executable scripts, binaries, or automated tasks detected.
Audit Metadata