build-cognitive-execution-engine
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by interpolating potentially untrusted external data into subagent prompt templates.
- Ingestion points: Untrusted data enters the agent context via placeholders such as
{{TASK_DESCRIPTION}}and{{CONTEXT}}inimplementer-prompt.md, and{{SPEC}}and{{IMPLEMENTATION_SUMMARY}}inspec-reviewer-prompt.md. - Boundary markers: The templates use Markdown headers and triple-dash delimiters (
---) to separate sections, but they lack explicit escaping or 'ignore embedded instructions' shielding for the interpolated variables. - Capability inventory: Subagents are granted tool access via
{{ALLOWED_TOOLS}}and are explicitly instructed to performsoftwareimplementation, which involves writing and verifying code. - Sanitization: There is no evidence of input validation, escaping, or filtering for the external content before it is interpolated into the prompts.
- Ingestion points: Untrusted data enters the agent context via placeholders such as
Audit Metadata