wiki-researcher

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute specific shell commands to determine the repository state, including git remote get-url origin and git rev-parse --abbrev-ref HEAD. These are standard, low-risk informational commands used for environment discovery in developer tools.- [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it is designed to read and process the contents of an entire codebase, which is untrusted external data.
  • Ingestion points: Reading local source code files throughout the repository during the 'Core Invariants' and 'Process' phases.
  • Boundary markers: None explicitly defined to separate file content from the agent's instructions.
  • Capability inventory: Execution of git discovery commands and broad file-system read access within the workspace.
  • Sanitization: No technical sanitization of file content is specified, though the instructions mandate a high 'Evidence Standard' and 'Zero Tolerance for Shallow Research' which encourages the agent to verify claims against actual code structure.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 06:11 PM