ae-generate-tracking-plan
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute various shell commands using the
ae-clitool. These commands handle plan generation (ae-cli tracking plan draft), authentication (ae-cli auth login), and data synchronization (ae-cli tracking plan upload). The CLI is a vendor-specific resource associated with the author 'thinkingaiagenticengine'. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external sources, including product requirements documents (PRDs) in various formats (PDF, DOCX, XLSX, PPTX) and application codebases. This ingestion surface is used to extract tracking definitions. While this creates a potential for indirect prompt injection, the skill mitigates risks through a mandatory 5-segment human-in-the-loop review process (Phase 2
- Refine) and automated schema validation before any data is uploaded to the AE platform.
- [DATA_EXPOSURE]: The skill accesses local project files and configuration data stored in the
.ae-cli/directory. It also manages project-specific identifiers and tokens. These actions are restricted to the local workspace and the designated AE platform host provided by the user.
Audit Metadata