file-operations

Pass

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill requests and utilizes the 'Bash' tool to handle system-level operations such as streaming large binary files and executing system commands ('stat', 'find'). This provides the agent with an expansive execution environment.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its ability to read and process arbitrary file content from the filesystem.
  • Ingestion points: Data enters the agent's context through the 'read_file' and 'search_files' operations defined in schema.yaml.
  • Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions when interpolating file content into prompts.
  • Capability inventory: The skill possesses high-privilege capabilities including shell execution ('Bash'), file modification ('Write', 'Edit'), and recursive deletion ('delete_directory').
  • Sanitization: There is no protocol for sanitizing or validating ingested file content before the agent processes it.
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 05:16 PM
Security Audit — agent-trust-hub — file-operations