tailrocks-reconcile
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell scripts located within the repository, specifically
roadmap/<slug>/goal/check.sh, and runs 'done criteria' and gate commands (goal/START.md) parsed from repository files. - [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes content from the repository, external registries, and web sources that could contain malicious instructions designed to influence agent behavior.
- Ingestion points: Reads
README.md,plan/*.md, andverification/files within theroadmap/<slug>/directory. - Boundary markers: Instructions explicitly direct the agent to treat repository and web content as evidence only and to flag any embedded instructions.
- Capability inventory: Includes shell command execution, Git operations (commit, push, move, remove), and writing to markdown files.
- Sanitization: Relies on the model's ability to identify and disregard instructions embedded in the processed data.
- [DYNAMIC_EXECUTION]: The skill dynamically executes commands extracted from text-based plan files to verify the status of roadmap items.
Audit Metadata