bkend-cookbook
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides links to external documentation hosted on GitHub (
github.com/popup-studio-ai/bkend-docs). These are utilized as live references for the agent to fetch current cookbook and troubleshooting information via web tools. - [INDIRECT_PROMPT_INJECTION]: The skill defines an attack surface for indirect prompt injection by instructing the agent to fetch and process external data from documentation repositories.
- Ingestion points: Documentation URLs listed under 'Official Documentation' in
SKILL.md. - Boundary markers: Absent; there are no explicit instructions for the agent to ignore potential instructions embedded within the fetched markdown files.
- Capability inventory: The skill has access to
Bash,Write,Edit, and various backend management tools (mcp__bkend__*), which could be targets for malicious instructions in external content. - Sanitization: Absent; the skill does not specify validation or filtering for the retrieved documentation content.
Audit Metadata