exec-cockpit
Pass
Audited by Gen Agent Trust Hub on Aug 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process leadership transition data, including "open loops", "partner deals", and "investor threads". These inputs represent external data sources that could potentially contain malicious instructions intended to influence agent behavior during document generation.
- Ingestion points: User-supplied transition data, relationship threads, and deal information (SKILL.md).
- Boundary markers: The skill refers to CLAUDE.md for guardrails but does not define specific delimiters for interpolating external data within the instructions.
- Capability inventory: Execution of document rendering tools (tools/render_brand_html.py) and drafting of recurring updates.
- Sanitization: No explicit sanitization or validation of input data is described within this template.
- [DYNAMIC_EXECUTION]: The skill utilizes a local Python script to perform document styling and rendering.
- Evidence: The instruction "Output: HTML styled with brand-assets/ (via tools/render_brand_html.py)" indicates the invocation of external logic to process generated content.
Audit Metadata