portfolio
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data (projects, research, and artifacts) which could contain malicious instructions designed to influence the agent's behavior during the portfolio building process.
- Ingestion points: The skill performs an 'inventory sweep' and 'inspects projects, artifacts, metrics, research, screenshots, source files, and testimonials' as described in
SKILL.md(Step 2: Inventory) and referenced inassets/portfolio-workbook.md. - Boundary markers: The skill does not implement specific delimiters or 'ignore' instructions for the data it processes from these external sources.
- Capability inventory: The skill possesses the capability to read local files, generate content via routing to other skills (e.g.,
humanizer,case-study), and perform remote operations such as publishing to GitHub via thegithub:yeettool. - Sanitization: No explicit sanitization, filtering, or escaping logic is defined for the content extracted from external artifacts before it is incorporated into the agent's context or output.
Audit Metadata