ai-readiness-assessment
Pass
Audited by Gen Agent Trust Hub on Aug 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external, potentially untrusted data sources including business documentation and codebases as described in its methodology. \n
- Ingestion points: Document review and codebase analysis are explicitly mentioned as information-gathering channels in references/methodology.md. \n
- Boundary markers: The instructions lack delimiters or explicit 'ignore embedded instructions' warnings for when the agent processes these external materials. \n
- Capability inventory: The skill has access to sensitive tools including
Bash,Write,Read, andWebFetchas defined in the SKILL.md frontmatter. \n - Sanitization: No evidence of input validation, escaping, or filtering of external content is present in the provided instructions or methodology.
Audit Metadata