candango-uat
Pass
Audited by Gen Agent Trust Hub on May 26, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill processes data from external documentation and design artifacts, creating a surface for indirect prompt injection.
- Ingestion points: As described in SKILL.md, the agent reads business definitions from context, feature plans, issue criteria, and local feature context files such as docs/features//context.md.
- Boundary markers: The instructions lack delimiters or explicit warnings to ignore potential instructions embedded in the ingested documents.
- Capability inventory: In SKILL.md, the agent is directed to read various project files and write output to docs/features//uat.md.
- Sanitization: There are no provisions for sanitizing or validating the content extracted from the external source files.
- [NO_CODE]: The skill consists solely of markdown and configuration files; it does not ship with or execute any external scripts or binary files.
Audit Metadata