trellis-finish-work
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local Python scripts located in the ./.trellis/scripts/ directory and standard git commands. These actions are aligned with the skill's stated purpose of managing task archives and session journals within a local development environment.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from local script outputs and git status to identify tasks and commits. * Ingestion points: Output from get_context.py and git status --porcelain. * Boundary markers: None observed in the instructions. * Capability inventory: Execution of local Python scripts via the shell. * Sanitization: None explicitly defined for processing external script output.
Audit Metadata