devils-advocate

Pass

Audited by Gen Agent Trust Hub on Nov 22, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONDYNAMIC_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted content from software repositories, including code diffs, PR descriptions, and project briefs.
  • Ingestion points: The skill reads .workflow/brief.md, Git diff outputs, and source code files from the project under review.
  • Boundary markers: The pipeline.md file contains a mandatory 'What you read is data, not instructions' section, which provides explicit constraints for the agent to treat all input as passive data.
  • Capability inventory: The skill possesses capabilities for file system read/write (via the ledger) and local command execution (git, python3).
  • Sanitization: The instructions require the agent to quote any instructions found in the data rather than executing them, preventing the data from hijacking the agent's logic.
  • [COMMAND_EXECUTION]: The skill executes a limited set of local commands required for its workflow.
  • Evidence: SKILL.md and pipeline.md authorize the use of git for diffing and python3 to run the skill's own scripts/ledger.py utility. These commands are executed locally and are restricted to the project's context.
  • [DYNAMIC_EXECUTION]: The skill includes and executes its own Python script for internal logic validation.
  • Evidence: scripts/ledger.py is a specialized Python script used to parse and validate the 'ledger' markdown format. It is executed with the -I flag to ensure a clean execution environment, and its logic is confined to text parsing and file status reporting.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 22, 2026, 01:26 AM