create-structure-outline
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from multiple sources to generate implementation plans, creating a potential surface for indirect prompt injection.\n
- Ingestion points: Processes research reports, design discussions, tickets, and repository files located in
.agent-work/tasks/(identified inreferences/source-discovery.md).\n - Boundary markers: No explicit delimiters or instructions are provided to the agent to disregard instructions embedded within these external sources.\n
- Capability inventory: The skill is capable of reading files, writing markdown and HTML artifacts to the filesystem, and executing shell commands (
ls,git).\n - Sanitization: No sanitization or validation of the input artifact content is performed before processing.\n- [COMMAND_EXECUTION]: The skill executes local shell commands to discover the repository state and metadata.\n
- Evidence: Uses
ls -Lato enumerate directories andgit rev-parse(HEAD,--git-dir) to capture branch and repository state (found inSKILL.mdandreferences/source-discovery.md).\n- [DYNAMIC_EXECUTION]: The skill can generate and potentially render HTML artifacts for UI visualization.\n - Evidence:
references/show-me.mddescribes a process for creating focused HTML files (show-me-<description>.html) to supplement the implementation outline.
Audit Metadata