tsg-flow-task-creator
Pass
Audited by Gen Agent Trust Hub on Nov 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes a bundled Python script (
scripts/validate_plan.py) to perform structural validation of implementation plans. This is a controlled execution of a local file provided within the skill's own package for quality assurance purposes. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process PRD and TechSpec files, which could theoretically contain malicious instructions. The skill mitigates this risk through instructional constraints that require referencing source documents by anchor rather than direct copying, and by utilizing a strict validation script to ensure the generated output conforms to an expected schema.
- [SAFE]: The skill does not perform any network operations, access sensitive system directories, use obfuscation, or execute remote code from untrusted sources. All operations are local and consistent with the stated purpose of task management and validation.
Audit Metadata